Alternatives and similar repositories for alignment_faking_public

Users that are interested in alignment_faking_public are comparing it to the libraries listed below

• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆180Updated last year
• jacobdunefsky / transcoder_circuits
  ☆168Updated 10 months ago
• saprmarks / feature-circuits
  ☆186Updated 2 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆240Updated 11 months ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆68Updated last week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆76Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆211Updated last week
• redwoodresearch / Easy-Transformer
  ☆122Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆269Updated 3 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆124Updated 6 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆116Updated last year
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆102Updated 2 weeks ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 4 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆264Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆201Updated 10 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆269Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• adamkarvonen / SAEBench
  ☆121Updated 2 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated 10 months ago
• neelnanda-io / Crosscoders
  ☆54Updated 9 months ago
• saprmarks / geometry-of-truth
  ☆91Updated last year
• METR / task-standard
  METR Task Standard
  ☆159Updated 7 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆127Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 9 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆78Updated 6 months ago
• KihoPark / linear_rep_geometry
  ☆106Updated 7 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆128Updated 2 months ago
• curt-tigges / probity
  ☆17Updated 5 months ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆90Updated last week