Alternatives and similar repositories for alignment_faking_public

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

• ArthurConmy / Automatic-Circuit-Discovery
  ☆231Updated 9 months ago
• EleutherAI / delphi
  Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …
  ☆192Updated last week
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆162Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆70Updated 2 months ago
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆112Updated last year
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆112Updated 4 months ago
• saprmarks / feature-circuits
  ☆182Updated 3 months ago
• jacobdunefsky / transcoder_circuits
  ☆140Updated 7 months ago
• redwoodresearch / Easy-Transformer
  ☆121Updated 11 months ago
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆53Updated 2 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• IBM / activation-steering
  General-purpose activation steering library
  ☆83Updated 2 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆56Updated 8 months ago
• saprmarks / geometry-of-truth
  ☆87Updated 11 months ago
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆218Updated 9 months ago
• Aaquib111 / edge-attribution-patching
  Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"
  ☆40Updated last year
• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆238Updated last month
• aypan17 / machiavelli
  ☆137Updated 8 months ago
• adamkarvonen / SAEBench
  ☆105Updated last month
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆23Updated 7 months ago
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆122Updated last year
• hannamw / EAP-IG
  ☆40Updated last month
• ajyl / dpo_toxic
  A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.
  ☆74Updated 4 months ago
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year
• HoagyC / sparse_coding
  Using sparse coding to find distributed representations used by neural networks.
  ☆259Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆109Updated last year
• 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…
  ☆128Updated last month
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆77Updated 7 months ago
• milesaturpin / cot-unfaithfulness
  ☆45Updated last year