andyrdt / refusal_direction

Related projects ⓘ

Alternatives and complementary repositories for refusal_direction

• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆154Updated last month
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆65Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆97Updated 5 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆99Updated last week
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆78Updated last year
• saprmarks / feature-circuits
  ☆105Updated last month
• allenai / WildBench
  Benchmarking LLMs with Challenging Tasks from Real Users
  ☆195Updated 2 weeks ago
• OSU-NLP-Group / GrokkedTransformer
  Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'
  ☆161Updated last month
• EleutherAI / sae-auto-interp
  ☆107Updated this week
• da03 / Internalize_CoT_Step_by_Step
  ☆102Updated last month
• WildEval / ZeroEval
  A simple unified framework for evaluating LLMs
  ☆145Updated last week
• paul-rottger / exaggerated-safety
  Röttger et al. (2023): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"
  ☆63Updated 10 months ago
• felipemaiapolo / tinyBenchmarks
  Evaluating LLMs with fewer examples
  ☆134Updated 7 months ago
• architsharma97 / dpo-rlaif
  ☆90Updated 4 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆61Updated last week
• shengliu66 / ICV
  Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering
  ☆144Updated last month
• ericwtodd / function_vectors
  Function Vectors in Large Language Models (ICLR 2024)
  ☆119Updated last month
• msclar / formatspread
  Code accompanying "How I learned to start worrying about prompt formatting".
  ☆95Updated last month
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆62Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆84Updated 7 months ago
• LoryPack / LLM-LieDetector
  Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"
  ☆62Updated 5 months ago
• kanishkg / stream-of-search
  Repository for the paper Stream of Search: Learning to Search in Language
  ☆91Updated 3 months ago
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆89Updated 5 months ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆157Updated last month
• davidbau / baukit
  ☆170Updated 8 months ago
• ryoungj / ObsScaling
  [NeurIPS'24 Spotlight] Observational Scaling Laws
  ☆44Updated last month
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆84Updated 8 months ago
• saprmarks / geometry-of-truth
  ☆71Updated 3 months ago
• openai / safety-rbr-code-and-data
  Code and example data for the paper: Rule Based Rewards for Language Model Safety
  ☆158Updated 4 months ago
• google-deepmind / mishax
  ☆101Updated 3 months ago