{"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":"/code/load-activations","entry":"load_activations","source":"Syntology graph, per-sample; not an archive number","read_at":"2026-09-24T18:15:14+00:00","claim":"Names are grouped by exact entry-name string. Same-named routines are NOT asserted to be equivalent; 'ran' means executed on a synthesized fixture, not correctness. n_samples_ran = sum of by_status over every status except 'unverified' (ran_draft_wrong and ran_fixture are failures of Syntology's instrument, not of the code); n_papers_ran = papers with at least one such sample.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"n_papers":5,"n_papers_ran":2,"units":"n_samples, n_samples_ran, n_samples_fingerprinted and by_status count distinct code bodies (code_sha256); n_places and n_places_pointer_only count places, one per (paper, code body) pair, which is also the unit of the samples list","n_samples":6,"n_samples_ran":2,"n_samples_fingerprinted":0,"n_places":6,"n_places_pointer_only":2,"by_status":{"ran_honours":0,"ran_violates":0,"ran_draft_wrong":1,"ran_fixture":0,"ran":1,"unverified":4},"syntology":{"atlas_url":null,"mcp":null,"mcp_per_sample":{"tool":"get_code","arguments_in":"samples[].mcp_get_code"},"developers":"https://syntology.ai/developers"},"samples":[{"arxiv_id":"2601.20420","paper":"/paper/arxiv-2601-20420","title":"Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"JoshEngels/SAE-Probes","path":"train_sae_probes.py","file_url":"https://github.com/JoshEngels/SAE-Probes/blob/HEAD/train_sae_probes.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"00330f81f32ca750","mcp_get_code":{"code_sha256":"00330f81f32ca750"}},{"arxiv_id":"2601.20420","paper":"/paper/arxiv-2601-20420","title":"Concept Component Analysis: A Principled Approach for Concept Extraction in LLMs","date":null,"month_inferred_from_arxiv_id":"2026-01","title_source":"syntology","repo":"JoshEngels/SAE-Probes","path":"generate_sae_activations.py","file_url":"https://github.com/JoshEngels/SAE-Probes/blob/HEAD/generate_sae_activations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"6331194a2c955ad8","mcp_get_code":{"code_sha256":"6331194a2c955ad8"}},{"arxiv_id":"2509.00544","paper":"/paper/arxiv-2509-00544","title":"When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced Misalignment","date":null,"month_inferred_from_arxiv_id":"2025-09","title_source":"syntology","repo":"seacowx/When-Thinking-Backfires","path":"RAS/compute_entanglement.py","file_url":"https://github.com/seacowx/When-Thinking-Backfires/blob/HEAD/RAS/compute_entanglement.py","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"b25ab8aa4af3b611","mcp_get_code":{"code_sha256":"b25ab8aa4af3b611"}},{"arxiv_id":"2507.03167","paper":"/paper/adversarial-manipulation-of-reasoning-models","title":"Adversarial Manipulation of Reasoning Models using Internal Representations","date":"2025-07-03","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"ky295/reasoning-manipulation","path":"interventions/create_ortho_model.py","file_url":"https://github.com/ky295/reasoning-manipulation/blob/HEAD/interventions/create_ortho_model.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"f5e16e8e7a8d83d1","mcp_get_code":{"code_sha256":"f5e16e8e7a8d83d1"}},{"arxiv_id":"2407.04108","paper":"/paper/future-events-as-backdoor-triggers","title":"Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs","date":"2024-07-04","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"sbp354/future_triggered_backdoors","path":"future_probing/linear_probes/utils/model_utils.py","file_url":"https://github.com/sbp354/future_triggered_backdoors/blob/HEAD/future_probing/linear_probes/utils/model_utils.py","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"code_sha256_prefix":"6c8235303d623c0c","mcp_get_code":{"code_sha256":"6c8235303d623c0c"}},{"arxiv_id":"2306.03819","paper":"/paper/leace-perfect-linear-concept-erasure-in","title":"LEACE: Perfect linear concept erasure in closed form","date":"2023-06-06","month_inferred_from_arxiv_id":null,"title_source":"archive","repo":"FairUnlearn/detoxai","path":"src/detoxai/cavs/extract_activations.py","file_url":"https://github.com/FairUnlearn/detoxai/blob/HEAD/src/detoxai/cavs/extract_activations.py","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"code_sha256_prefix":"7c2b37a6331c6391","mcp_get_code":{"code_sha256":"7c2b37a6331c6391"}}]}