anthropics / sleeper-agents-paper

Related projects ⓘ

Alternatives and complementary repositories for sleeper-agents-paper

• andyrdt / refusal_direction
  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".
  ☆123Updated last month
• GraySwanAI / circuit-breakers
  Improving Alignment and Robustness with Circuit Breakers
  ☆154Updated last month
• 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…
  ☆82Updated 6 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆44Updated last month
• METR / vivaria
  Vivaria is METR's tool for running evaluations and conducting agent elicitation research.
  ☆63Updated this week
• max-andr / adversarial-random-search-gpt4
  Adversarial Attacks on GPT-4 via Simple Random Search [Dec 2023]
  ☆42Updated 6 months ago
• saprmarks / feature-circuits
  ☆105Updated last month
• EleutherAI / sae-auto-interp
  ☆107Updated this week
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆65Updated last month
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆78Updated last year
• ethz-spylab / rlhf_trojan_competition
  Finding trojans in aligned LLMs. Official repository for the competition hosted at SaTML 2024.
  ☆107Updated 5 months ago
• google-deepmind / mishax
  ☆101Updated 3 months ago
• METR / task-standard
  METR Task Standard
  ☆124Updated 3 weeks ago
• AsaCooperStickland / situational-awareness-evals
  Measuring the situational awareness of language models
  ☆33Updated 9 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…
  ☆25Updated 5 months ago
• ryoungj / ToolEmu
  [ICLR'24 Spotlight] A language model (LM)-based emulation framework for identifying the risks of LM agents with tool use
  ☆115Updated 8 months ago
• mlcommons / modelbench
  Run safety benchmarks against AI models and view detailed reports showing how well they performed.
  ☆62Updated this week
• JonasGeiping / carving
  Package to optimize Adversarial Attacks against (Large) Language Models with Varied Objectives
  ☆64Updated 8 months ago
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆99Updated last week
• ucl-dark / llm_debate
  Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"
  ☆84Updated 7 months ago
• callummcdougall / sae_visualizer
  ☆24Updated 7 months ago
• JoshEngels / MultiDimensionalFeatures
  Code for reproducing our paper "Not All Language Model Features Are Linear"
  ☆61Updated last week
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆157Updated last month
• ethz-spylab / agentdojo
  A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
  ☆62Updated last week
• rishub-tamirisa / tamper-resistance
  Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"
  ☆38Updated last month
• nrimsky / CAA
  Steering Llama 2 with Contrastive Activation Addition
  ☆97Updated 5 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆62Updated last year
• Confirm-Solutions / flrt
  Fluent student-teacher redteaming
  ☆13Updated 3 months ago
• jacobdunefsky / transcoder_circuits
  ☆44Updated this week
• JacobPfau / fillerTokens
  ☆49Updated 6 months ago