Alternatives and similar repositories for alignment_faking_public:

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

• amack315 / unsupervised-steering-vectors
  ☆31Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆64Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆49Updated this week
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆64Updated 2 weeks ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆99Updated 2 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆18Updated 5 months ago
• jacobdunefsky / transcoder_circuits
  ☆111Updated 5 months ago
• milesaturpin / cot-unfaithfulness
  ☆42Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆147Updated 11 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• Jiaxin-Wen / MisleadLM
  Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""
  ☆14Updated 6 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆221Updated 7 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆54Updated 6 months ago
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆72Updated last month
• EleutherAI / w2s
  ☆23Updated 7 months ago
• callummcdougall / sae_visualizer
  ☆26Updated last year
• redwoodresearch / Easy-Transformer
  ☆114Updated 9 months ago
• jbloomAus / SAEDashboard
  ☆38Updated 2 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆73Updated 5 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆31Updated 11 months ago
• saprmarks / geometry-of-truth
  ☆82Updated 8 months ago
• adamkarvonen / SAEBench
  ☆93Updated 3 weeks ago
• rishub-tamirisa / tamper-resistance
  [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆54Updated 2 months ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆198Updated 7 months ago
• neelnanda-io / Crosscoders
  ☆39Updated 5 months ago
• saprmarks / feature-circuits
  ☆164Updated 3 weeks ago
• marcus-jw / Targeted-Manipulation-and-Deception-in-LLMs
  Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-tur…
  ☆15Updated 5 months ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆76Updated last month
• ejnnr / cupbearer
  A library for mechanistic anomaly detection
  ☆21Updated 3 months ago