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
  ☆248Updated last year
• saprmarks / feature-circuits
  ☆191Updated 2 weeks ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆191Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆78Updated 3 months ago
• redwoodresearch / Easy-Transformer
  ☆127Updated last year
• jacobdunefsky / transcoder_circuits
  ☆181Updated 11 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆98Updated 2 years ago
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆77Updated last week
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆219Updated last week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆126Updated 8 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆66Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆117Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆280Updated last year
• neelnanda-io / Crosscoders
  ☆55Updated 11 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆130Updated 2 years ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆224Updated 10 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆59Updated last year
• KihoPark / linear_rep_geometry
  ☆108Updated 8 months ago
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆114Updated last month
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆292Updated 4 months ago
• saprmarks / geometry-of-truth
  ☆92Updated last year
• aypan17 / machiavelli
  ☆138Updated 3 months ago
• curt-tigges / probity
  ☆19Updated 6 months ago
• adamkarvonen / SAEBench
  ☆131Updated last week
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆296Updated 10 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆55Updated 5 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆276Updated last year
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆24Updated 3 weeks ago
• davidbau / baukit
  ☆236Updated last year
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆25Updated 11 months ago