Alternatives and similar repositories for refusal_direction

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

• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆101Updated 3 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆208Updated 8 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆154Updated last year
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆180Updated this week
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆97Updated 3 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆93Updated last year
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆167Updated last month
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆247Updated last year
• IBM / activation-steering
  General-purpose activation steering library
  ☆74Updated 3 weeks ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆184Updated 6 months ago
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆116Updated this week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆200Updated 5 months ago
• jacobdunefsky / transcoder_circuits
  ☆120Updated 6 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆248Updated 10 months ago
• centerforaisafety / wmdp
  WMDP is a LLM proxy benchmark for hazardous knowledge in bio, cyber, and chemical security. We also release code for RMU, an unlearning m…
  ☆121Updated this week
• allenai / WildBench
  Benchmarking LLMs with Challenging Tasks from Real Users
  ☆223Updated 7 months ago
• saprmarks / feature-circuits
  ☆170Updated last month
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• epfl-dlab / llm-latent-language
  Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".
  ☆76Updated last year
• da03 / Internalize_CoT_Step_by_Step
  ☆174Updated last month
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆89Updated last week
• shengliu66 / ICV
  Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
  ☆174Updated 3 months ago
• davidbau / baukit
  ☆209Updated last year
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆119Updated 11 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆547Updated last week
• allenai / wildguard
  Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  ☆77Updated 6 months ago
• LLM-Tuning-Safety / LLMs-Finetuning-Safety
  We jailbreak GPT-3.5 Turbo’s safety guardrails by fine-tuning it on only 10 adversarially designed examples, at a cost of less than $0.20…
  ☆298Updated last year
• redwoodresearch / Easy-Transformer
  ☆116Updated 9 months ago
• saprmarks / geometry-of-truth
  ☆83Updated 9 months ago
• adamkarvonen / SAEBench
  ☆97Updated last month