Alternatives and similar repositories for alignment_faking_public:

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

• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆38Updated 2 months ago
• ejones313 / auditing-llms
  ☆51Updated last year
• adamkarvonen / SAEBench
  ☆41Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆78Updated last month
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆62Updated last year
• EleutherAI / elk-generalization
  Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…
  ☆26Updated 7 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆61Updated 2 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆46Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆114Updated 7 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆85Updated last year
• milesaturpin / cot-unfaithfulness
  ☆34Updated last year
• saprmarks / geometry-of-truth
  ☆75Updated 5 months ago
• EleutherAI / sae-auto-interp
  ☆135Updated this week
• hannamw / EAP-IG
  ☆17Updated last month
• 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…
  ☆92Updated 8 months ago
• jacobdunefsky / transcoder_circuits
  ☆53Updated 2 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"
  ☆64Updated 7 months ago
• OpenMOSS / Language-Model-SAEs
  For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.
  ☆82Updated this week
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆155Updated 3 months ago
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆174Updated 3 months ago
• redwoodresearch / Easy-Transformer
  ☆106Updated 5 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
• logix-project / logix
  AI Logging for Interpretability and Explainability🔬
  ☆97Updated 7 months ago
• IBM / activation-steering
  General-purpose activation steering library
  ☆41Updated 2 weeks ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆66Updated last month
• amack315 / unsupervised-steering-vectors
  ☆28Updated 8 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆27Updated 7 months ago
• saprmarks / feature-circuits
  ☆132Updated 3 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆66Updated last year