Papers › Mamba Knockout for Unraveling Factual Information Flow

Mamba Knockout for Unraveling Factual Information Flow

30 May 2025arXiv:2505.24244archive 2025-07-28

Nir Endy, Idan Daniel Grosbard, Yuval Ran-Milo, Yonatan Slutzky, Itay Tshuva, Raja Giryes

This paper investigates the flow of factual information in Mamba State-Space Model (SSM)-based language models. We rely on theoretical and empirical connections to Transformer-based architectures and their attention mechanisms. Exploiting this relationship, we adapt attentional interpretability techniques originally developed for Transformers--specifically, the Attention Knockout methodology--to both Mamba-1 and Mamba-2. Using them we trace how information is transmitted and localized across tokens and layers, revealing patterns of subject-token information emergence and layer-wise dynamics. Notably, some phenomena vary between mamba models and Transformer based models, while others appear universally across all models inspected--hinting that these may be inherent to LLMs in general. By further leveraging Mamba's structured factorization, we disentangle how distinct "features" either enable token-to-token information exchange or enrich individual tokens, thus offering a unified lens to understand Mamba internal operations.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2505.24244")

Code

Syntology Ran 2 of 6 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: official repository: 6 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nirendy/mamba-knockout officialmentioned in paperMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

6 samples harvested; 2 ran; 0 honoured the contract we drafted; 4 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
1ran · fixture could not drive it
4unverified

Licence: 0 of the 6 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from nirendy/mamba-knockout. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

repeat_kv nirendy/mamba-knockout/src/experiments/knockout/llama/sdpa_attention.py official repository ran · fixture could not drive it fingerprinted MIT (permissive) · 3c76e52815c5401d · report
silu nirendy/mamba-knockout/src/experiments/knockout/mamba/mamba2/minimal_mamba2.py official repository ran · our draft was wrong fingerprinted MIT (permissive) · 8558535d4b8ed416 · report
materialize_ssm_attention nirendy/mamba-knockout/src/experiments/knockout/mamba/mamba1/helpers/knockout_scan.py official repository unverified MIT (permissive) · 0f31e1dfe2cd3cb7 · report
materialize_ssm_transition nirendy/mamba-knockout/src/experiments/knockout/mamba/mamba1/helpers/knockout_scan.py official repository unverified MIT (permissive) · d17cc45474e76592 · report
rms_forward nirendy/mamba-knockout/src/experiments/knockout/mamba/mamba1/falcon_variant.py official repository unverified MIT (permissive) · 73c4d0965a947444 · report
scaled_dot_product_attention nirendy/mamba-knockout/src/experiments/knockout/llama/scaled_dot_product_attention.py official repository unverified MIT (permissive) · bec2160c46dd3280 · report

Tasks

Mamba

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMambaMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections