Alternatives and similar repositories for alignment_faking_public

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

• ArthurConmy / Automatic-Circuit-Discovery
  ☆253Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆193Updated last year
• jacobdunefsky / transcoder_circuits
  ☆188Updated last year
• saprmarks / feature-circuits
  ☆194Updated 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 …
  ☆225Updated last week
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆283Updated 2 years ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆284Updated last year
• redwoodresearch / Easy-Transformer
  ☆129Updated last year
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆119Updated 2 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆99Updated 2 years ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆227Updated 11 months ago
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆299Updated 5 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆60Updated last year
• neelnanda-io / Crosscoders
  ☆56Updated last year
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆128Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆129Updated 8 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆301Updated 11 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆80Updated 4 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 6 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆121Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆242Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆66Updated 2 years ago
• adamkarvonen / SAEBench
  ☆136Updated this week
• saprmarks / geometry-of-truth
  ☆94Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆80Updated this week
• aypan17 / machiavelli
  ☆141Updated 3 months ago
• METR / task-standard
  METR Task Standard
  ☆167Updated 9 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆96Updated 2 years ago
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆24Updated last month