Alternatives and similar repositories for sleeper-agents

Users that are interested in sleeper-agents are comparing it to the libraries listed below

• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆57Updated 8 months ago
• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆23Updated 7 months ago
• METR / RE-Bench
  ☆92Updated 2 months ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆14Updated 7 months ago
• redwoodresearch / alignment_faking_public
  ☆69Updated last month
• 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…
  ☆28Updated last year
• KoyenaPal / future-lens
  Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State
  ☆18Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆53Updated 2 months ago
• METR / task-standard
  METR Task Standard
  ☆154Updated 5 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆115Updated 4 months ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆19Updated 8 months ago
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆70Updated 2 months ago
• 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 …
  ☆193Updated this week
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆112Updated last year
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆81Updated last year
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆73Updated this week
• saprmarks / feature-circuits
  ☆182Updated 3 months ago
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆206Updated 7 months ago
• callummcdougall / sae_visualizer
  ☆28Updated last year
• ApolloResearch / apd
  Attribution-based Parameter Decomposition
  ☆26Updated last month
• adamkarvonen / SAEBench
  ☆105Updated last month
• neelnanda-io / Crosscoders
  ☆47Updated 7 months ago
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆49Updated 9 months ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆95Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆122Updated last year
• redwoodresearch / Easy-Transformer
  ☆121Updated 11 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆55Updated 9 months ago