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
  ☆238Updated 10 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆176Updated last year
• jacobdunefsky / transcoder_circuits
  ☆163Updated 9 months ago
• saprmarks / feature-circuits
  ☆184Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆122Updated 6 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆207Updated this week
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆264Updated last year
• safety-research / safety-tooling
  Inference API for many LLMs and other useful tools for empirical research
  ☆66Updated last week
• redwoodresearch / Easy-Transformer
  ☆122Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆76Updated last month
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆257Updated 2 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• IBM / activation-steering
  [ICLR 2025] General-purpose activation steering library
  ☆94Updated last month
• neelnanda-io / Crosscoders
  ☆53Updated 9 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆58Updated 10 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆114Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 3 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆126Updated last year
• KihoPark / linear_rep_geometry
  ☆103Updated 6 months ago
• saprmarks / geometry-of-truth
  ☆90Updated last year
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆76Updated 5 months ago
• science-of-finetuning / crosscoder_learning
  Modified to support crosscoder training.
  ☆22Updated last month
• wesg52 / sparse-probing-paper
  Sparse probing paper full code.
  ☆59Updated last year
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆212Updated 8 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆227Updated 11 months ago
• adamkarvonen / SAEBench
  ☆114Updated last month
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 9 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆40Updated last year