Alternatives and similar repositories for alignment_faking_public:

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

• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆94Updated last month
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆62Updated last month
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆166Updated this week
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆47Updated 5 months ago
• saprmarks / feature-circuits
  ☆157Updated this week
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆49Updated 5 months ago
• jacobdunefsky / transcoder_circuits
  ☆91Updated 4 months ago
• milesaturpin / cot-unfaithfulness
  ☆41Updated last year
• amack315 / unsupervised-steering-vectors
  ☆30Updated 11 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆216Updated 6 months ago
• redwoodresearch / Easy-Transformer
  ☆115Updated 8 months ago
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆137Updated 10 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆64Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆91Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 2 years ago
• stanfordnlp / axbench
  Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
  ☆63Updated 2 weeks ago
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆196Updated 6 months ago
• EleutherAI / w2s
  ☆23Updated 6 months ago
• KihoPark / linear_rep_geometry
  ☆91Updated 2 months ago
• Nix07 / finetuning
  This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…
  ☆25Updated last year
• callummcdougall / sae_visualizer
  ☆26Updated last year
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆103Updated last year
• adamkarvonen / SAEBench
  ☆81Updated last week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆121Updated last year
• 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…
  ☆14Updated 4 months ago
• saprmarks / geometry-of-truth
  ☆82Updated 8 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆73Updated 4 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆30Updated 10 months ago
• jbloomAus / SAEDashboard
  ☆34Updated last month
• ejones313 / auditing-llms
  ☆54Updated 2 years ago