Keeping language models honest by directly eliciting knowledge encoded in their activations.
☆226Oct 26, 2026Updated this week
Alternatives and similar repositories for elk
Users that are interested in elk are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆292Mar 2, 2024Updated 2 years ago
- Erasing concepts from neural representations with provable guarantees☆271Jan 27, 2025Updated last year
- Interpreting how transformers simulate agents performing RL tasks☆91Oct 23, 2023Updated 3 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- A dataset of alignment research and code to reproduce it☆80Jun 22, 2023Updated 3 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆74Jun 19, 2024Updated 2 years ago
- Measuring the situational awareness of language models☆43Feb 12, 2024Updated 2 years ago
- Tools for understanding how transformer predictions are built layer-by-layer☆619Aug 7, 2025Updated last year
- ☆17Jun 17, 2025Updated last year
- Machine Learning for Alignment Bootcamp☆88Oct 6, 2026Updated 3 weeks ago
- ☆45Nov 17, 2024Updated last year
- ☆20Jan 21, 2023Updated 3 years ago
- ☆21Feb 17, 2023Updated 3 years ago
- A library for mechanistic interpretability of GPT-style language models☆4,017Updated this week
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Contains random samples referenced in the paper "Sleeper Agents: Training Robustly Deceptive LLMs that Persist Through Safety Training".☆156Mar 9, 2024Updated 2 years ago
- ☆58Jun 30, 2023Updated 3 years ago
- gpt completions in vscode☆35Mar 24, 2023Updated 3 years ago
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- Code for our paper "Localizing Lying in Llama"☆15Apr 24, 2025Updated last year
- Understanding how features learned by neural networks evolve throughout training☆40Oct 24, 2024Updated 2 years ago
- ☆300Oct 1, 2024Updated 2 years ago
- Vivaria is METR's tool for running evaluations and conducting agent elicitation research.☆144Oct 7, 2026Updated 3 weeks ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Oct 7, 2024Updated 2 years ago
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- Code for paper "Factual Confidence of LLMs: on Reliability and Robustness of Current Estimators"☆17Dec 4, 2024Updated last year
- Utilities for the HuggingFace transformers library☆78Jan 21, 2023Updated 3 years ago
- (Model-written) LLM evals library☆19Dec 13, 2024Updated last year
- James' cookbook of evaluations and finetuning experiments☆36Feb 19, 2026Updated 8 months ago
- ☆24Jul 18, 2024Updated 2 years ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,137Updated this week
- ☆443Jul 2, 2024Updated 2 years ago
- Mechanistic Interpretability Visualizations using React☆372Apr 30, 2026Updated 6 months ago
- Inference-Time Intervention: Eliciting Truthful Answers from a Language Model☆587Jan 28, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- A library for activation patching based on nnsight.☆12May 27, 2025Updated last year
- ☆1,084Mar 6, 2024Updated 2 years ago
- ☆13May 7, 2023Updated 3 years ago
- This is the starter kit for the Trojan Detection Challenge 2023 (LLM Edition), a NeurIPS 2023 competition.☆92May 19, 2024Updated 2 years ago
- ☆62Nov 19, 2024Updated last year
- Quantifying degeneracy in toy models☆11Sep 6, 2024Updated 2 years ago
- Machine Learning for Alignment Bootcamp (MLAB).☆36Jan 24, 2022Updated 4 years ago