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
  ☆185Updated 4 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆123Updated 8 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆88Updated this week
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆92Updated this week
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆88Updated last year
• paul-rottger / xstest
  Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆84Updated last week
• EleutherAI / delphi
  ☆151Updated this week
• IBM / activation-steering
  General-purpose activation steering library
  ☆43Updated last month
• da03 / Internalize_CoT_Step_by_Step
  ☆149Updated last week
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆160Updated 3 months ago
• saprmarks / feature-circuits
  ☆142Updated 3 weeks ago
• shengliu66 / ICV
  Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
  ☆162Updated last week
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆182Updated 2 months ago
• XuandongZhao / weak-to-strong
  Weak-to-Strong Jailbreaking on Large Language Models
  ☆72Updated 11 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…
  ☆101Updated 9 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆68Updated 2 months ago
• tml-epfl / llm-adaptive-attacks
  Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks [ICLR 2025]
  ☆262Updated 3 weeks ago
• amack315 / unsupervised-steering-vectors
  ☆29Updated 9 months ago
• Princeton-SysML / Jailbreak_LLM
  ☆163Updated last year
• redwoodresearch / Easy-Transformer
  ☆109Updated 6 months ago
• ai-safety-foundation / sparse_autoencoder
  Sparse Autoencoder for Mechanistic Interpretability
  ☆216Updated 7 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆71Updated last year
• casper-hansen / OpenCoconut
  OpenCoconut implements a latent reasoning paradigm where we generate thoughts before decoding.
  ☆167Updated last month
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆46Updated 3 weeks ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆98Updated 10 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…
  ☆276Updated 11 months ago
• allenai / wildguard
  Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
  ☆61Updated 2 months ago
• jacobdunefsky / transcoder_circuits
  ☆55Updated 3 months ago
• EleutherAI / sparsify
  Sparsify transformers with SAEs and transcoders
  ☆461Updated this week
• ArthurConmy / Automatic-Circuit-Discovery
  ☆203Updated 4 months ago