Alternatives and similar repositories for evals

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

• EleutherAI / elk
  Keeping language models honest by directly eliciting knowledge encoded in their activations.
  ☆217Updated last week
• METR / task-standard
  METR Task Standard
  ☆172Updated last year
• METR / RE-Bench
  ☆133Updated 3 months ago
• aypan17 / machiavelli
  ☆144Updated 6 months ago
• meg-tong / sycophancy-eval
  datasets from the paper "Towards Understanding Sycophancy in Language Models"
  ☆102Updated 2 years ago
• justinchiu / openlogprobs
  Extract full next-token probabilities via language model APIs
  ☆248Updated last year
• anthropics / sleeper-agents-paper
  Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".
  ☆124Updated last year
• anthropics / ConstitutionalHarmlessnessPaper
  ☆250Updated 3 years ago
• TransformerLensOrg / CircuitsVis
  Mechanistic Interpretability Visualizations using React
  ☆318Updated last year
• METR / public-tasks
  ☆117Updated 2 weeks ago
• nrimsky / LM-exp
  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces
  ☆100Updated 2 years ago
• UKGovernmentBEIS / control-arena
  ControlArena is a collection of settings, model organisms and protocols - for running control experiments.
  ☆150Updated this week
• collin-burns / discovering_latent_knowledge
  ☆284Updated last year
• ArthurConmy / Automatic-Circuit-Discovery
  ☆267Updated last year
• TransluceAI / observatory
  A toolkit for describing model features and intervening on those features to steer behavior.
  ☆227Updated last month
• google-research / cascades
  Python library which enables complex compositions of language models such as scratchpads, chain of thought, tool use, selection-inference…
  ☆216Updated 3 weeks ago
• callummcdougall / sae_vis
  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
  ☆238Updated last year
• hendrycks / ethics
  Aligning AI With Shared Human Values (ICLR 2021)
  ☆314Updated 2 years ago
• normster / llm_rules
  RuLES: a benchmark for evaluating rule-following in language models
  ☆248Updated 11 months ago
• steering-vectors / steering-vectors
  Steering vectors for transformer language models in Pytorch / Huggingface
  ☆140Updated 11 months ago
• lukasberglund / reversal_curse
  ☆304Updated 2 years ago
• haizelabs / verdict
  Inference-time scaling for LLMs-as-a-judge.
  ☆327Updated 3 months ago
• google-deepmind / dangerous-capability-evaluations
  ☆65Updated last week
• ofirpress / self-ask
  Code and data for "Measuring and Narrowing the Compositionality Gap in Language Models"
  ☆323Updated 2 years ago
• rgreenblatt / arc_draw_more_samples_pub
  Draw more samples
  ☆198Updated last year
• EleutherAI / concept-erasure
  Erasing concepts from neural representations with provable guarantees
  ☆242Updated last year
• AlignmentResearch / tuned-lens
  Tools for understanding how transformer predictions are built layer-by-layer
  ☆565Updated 5 months ago
• UKGovernmentBEIS / inspect_evals
  Collection of evals for Inspect AI
  ☆349Updated this week
• neelnanda-io / 1L-Sparse-Autoencoder
  ☆132Updated 2 years ago
• google-deepmind / mishax
  ☆152Updated 4 months ago