{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unveiling-language-skills-under-circuits","title":"Unveiling Language Skills via Path-Level Circuit Discovery","arxiv_id":"2410.01334","date":"2024-10-02","proceeding":null,"authors":["Hang Chen","Jiaying Zhu","Xinyu Yang","Wenya Wang"],"abstract":"Circuit discovery with edge-level ablation has become a foundational framework for mechanism interpretability of language models. However, its focus on individual edges often overlooks the sequential, path-level causal relationships that underpin complex behaviors, thus potentially leading to misleading or incomplete circuit discoveries. To address this issue, we propose a novel path-level circuit discovery framework capturing how behaviors emerge through interconnected linear chain and build towards complex behaviors. Our framework is constructed upon a fully-disentangled linear combinations of ``memory circuits'' decomposed from the original model. To discover functional circuit paths, we leverage a 2-step pruning strategy by first reducing the computational graph to a faithful and minimal subgraph and then applying causal mediation to identify common paths of a specific skill, termed as skill paths. In contrast to circuit graph from existing works, we focus on the complete paths of a generic skill rather than on the fine-grained responses to individual components of the input. To demonstrate this, we explore three generic language skills, namely Previous Token Skill, Induction Skill and In-Context Learning Skill using our framework and provide more compelling evidence to substantiate stratification and inclusiveness of these skills.","url_abs":"https://arxiv.org/abs/2410.01334v2","url_pdf":"https://arxiv.org/pdf/2410.01334v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unveiling-language-skills-under-circuits","repo_url":"https://github.com/zodiark-ch/language-skill-of-llms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"disentanglement","task_name":"Disentanglement"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.01334","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.01334"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zodiark-ch/language-skill-of-llms","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"a2e2165007b7960e","entry":"get_logger","repo":"zodiark-ch/language-skill-of-llms","repo_kind":"official","path":"language_skill_icl.py","file_url":"https://github.com/zodiark-ch/language-skill-of-llms/blob/HEAD/language_skill_icl.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a2e2165007b7960e"}},{"code_sha256_prefix":"67deba6ae134ab72","entry":"get_token_rank","repo":"zodiark-ch/language-skill-of-llms","repo_kind":"official","path":"skill_analysis.py","file_url":"https://github.com/zodiark-ch/language-skill-of-llms/blob/HEAD/skill_analysis.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"67deba6ae134ab72"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}