Keeping language models honest by directly eliciting knowledge encoded in their activations.
☆217Mar 16, 2026Updated this week
Alternatives and similar repositories for elk
Users that are interested in elk are comparing it to the libraries listed below
Sorting:
- ☆283Mar 2, 2024Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆245Jan 27, 2025Updated last year
- Interpreting how transformers simulate agents performing RL tasks☆90Oct 23, 2023Updated 2 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28May 23, 2024Updated last year
- Machine Learning for Alignment Bootcamp☆82Apr 27, 2022Updated 3 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆574Aug 7, 2025Updated 7 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Jun 19, 2024Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,183Mar 13, 2026Updated last week
- Code for our paper "Localizing Lying in Llama"☆13Apr 24, 2025Updated 10 months ago
- Understanding how features learned by neural networks evolve throughout training☆41Oct 24, 2024Updated last year
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆137Mar 9, 2024Updated 2 years ago
- Measuring the situational awareness of language models☆40Feb 12, 2024Updated 2 years ago
- ☆20Feb 17, 2023Updated 3 years ago
- A dataset of alignment research and code to reproduce it☆78Jun 22, 2023Updated 2 years ago
- (Model-written) LLM evals library☆18Dec 13, 2024Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆22Updated this week
- Minimum Description Length probing for neural network representations☆20Jan 28, 2025Updated last year
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆135Feb 15, 2026Updated last month
- ☆20Jan 21, 2023Updated 3 years ago
- ☆13Jul 12, 2024Updated last year
- ☆278Oct 1, 2024Updated last year
- ☆44Nov 17, 2024Updated last year
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆258Sep 24, 2024Updated last year
- ☆336Jul 2, 2024Updated last year
- Utilities for the HuggingFace transformers library☆75Jan 21, 2023Updated 3 years ago
- Sparse Autoencoder for Mechanistic Interpretability☆294Jul 20, 2024Updated last year
- Script for downloading GitHub.☆13Sep 24, 2020Updated 5 years ago
- ☆11Jun 2, 2021Updated 4 years ago
- A repository for transformer critique learning and generation☆89Dec 7, 2023Updated 2 years ago
- Redwood Research's transformer interpretability tools☆15Apr 15, 2022Updated 3 years ago
- 📚📚📚📚📚📚📚📚📚 Reading everything☆15Mar 11, 2026Updated last week
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆209Dec 22, 2021Updated 4 years ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆90May 19, 2024Updated last year
- Inspect: A framework for large language model evaluations☆1,841Updated this week
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆863Updated this week
- Locating and editing factual associations in GPT (NeurIPS 2022)☆736Apr 20, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Oct 27, 2024Updated last year
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆573Jan 28, 2025Updated last year