Alternatives and similar repositories for sleeper-agents

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

• slavachalnev / SAE-TS
  Improving Steering Vectors by Targeting Sparse Autoencoder Features
  ☆24Updated 8 months ago
• 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
• METR / RE-Bench
  ☆95Updated 3 months ago
• ckkissane / crosscoder-model-diff-replication
  Open source replication of Anthropic's Crosscoders for Model Diffing
  ☆57Updated 9 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆120Updated 5 months ago
• ArthurConmy / Automatic-Circuit-Discovery
  ☆234Updated 10 months ago
• redwoodresearch / alignment_faking_public
  ☆70Updated 2 months ago
• amack315 / unsupervised-steering-vectors
  ☆32Updated last year
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆167Updated last year
• ApolloResearch / e2e_sae
  Sparse Autoencoder Training Library
  ☆54Updated 3 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 …
  ☆202Updated this week
• callummcdougall / sae_visualizer
  ☆28Updated last year
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆96Updated last year
• redwoodresearch / interp
  Redwood Research's transformer interpretability tools
  ☆14Updated 3 years ago
• FlyingPumba / InterpBench
  A benchmark for mechanistic discovery of circuits in Transformers
  ☆16Updated 7 months ago
• adamkarvonen / SAEBench
  ☆109Updated 3 weeks ago
• annahdo / implementing_activation_steering
  A collection of different ways to implement accessing and modifying internal model activations for LLMs
  ☆19Updated 9 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"
  ☆72Updated last year
• UFO-101 / auto-circuit
  A library for efficient patching and automatic circuit discovery.
  ☆73Updated 2 weeks 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
• explanare / ravel
  Evaluate interpretability methods on localizing and disentangling concepts in LLMs.
  ☆52Updated 10 months ago
• saprmarks / feature-circuits
  ☆183Updated 3 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆207Updated 7 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆86Updated last year
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆272Updated 7 months ago
• neelnanda-io / Crosscoders
  ☆51Updated 8 months ago
• saprmarks / geometry-of-truth
  ☆89Updated last year
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆37Updated last year
• montemac / activation_additions
  Algebraic value editing in pretrained language models
  ☆65Updated last year
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆124Updated last year