Alternatives and similar repositories for refusal_direction:

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

• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆174Updated 3 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆113Updated 7 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆78Updated last month
• EleutherAI / sae-auto-interp
  ☆135Updated this week
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆82Updated this week
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆85Updated last year
• da03 / Internalize_CoT_Step_by_Step
  ☆135Updated 3 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆149Updated 2 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆66Updated last month
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆175Updated last month
• shengliu66 / ICV
  Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
  ☆154Updated 3 months ago
• saprmarks / feature-circuits
  ☆131Updated 3 months ago
• paul-rottger / exaggerated-safety
  Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆77Updated last year
• redwoodresearch / Easy-Transformer
  ☆106Updated 5 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆176Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆207Updated last year
• WildEval / ZeroEval
  A simple unified framework for evaluating LLMs
  ☆164Updated 3 weeks ago
• allenai / WildBench
  Benchmarking LLMs with Challenging Tasks from Real Users
  ☆206Updated 2 months ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆40Updated 2 weeks ago
• cohere-ai / magikarp
  Code for the paper "Fishing for Magikarp"
  ☆139Updated this week
• EleutherAI / sae
  Sparse autoencoders
  ☆407Updated this week
• saprmarks / geometry-of-truth
  ☆75Updated 5 months ago
• architsharma97 / dpo-rlaif
  ☆93Updated 6 months ago
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆131Updated 3 months ago
• jacobdunefsky / transcoder_circuits
  ☆53Updated 2 months ago
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆64Updated 10 months ago
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆157Updated this week
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆95Updated 9 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆62Updated last year
• JacobPfau / fillerTokens
  ☆58Updated 8 months ago