James' cookbook of evaluations and finetuning experiments
☆36Feb 19, 2026Updated 8 months ago
Alternatives and similar repositories for latteries
Users that are interested in latteries are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Easily deploy my zsh and tmux configuration on new machines. Includes local and remote aliases to improve workflow.☆16Apr 23, 2026Updated 6 months ago
- Code and materials for "Weird Generalization and Inductive Backdoors"☆43Jan 11, 2026Updated 9 months ago
- Unified access to Large Language Model modules using NNsight☆121Updated this week
- A python sdk for LLM finetuning and inference on runpod infrastructure☆30Oct 13, 2026Updated 2 weeks ago
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆35Oct 5, 2026Updated 3 weeks ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆33Nov 11, 2025Updated 11 months ago
- Engine for collecting, uploading, and downloading model activations☆31Apr 2, 2025Updated last year
- Extract residual-stream activations and apply steering vectors (including activation oracles) to any vLLM model during inference.☆140Oct 13, 2026Updated 2 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆30Nov 20, 2024Updated last year
- ☆16Oct 13, 2025Updated last year
- ☆27Jul 8, 2026Updated 3 months ago
- ☆89Feb 25, 2025Updated last year
- ☆61Feb 11, 2025Updated last year
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆146Feb 8, 2026Updated 8 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- ☆12Sep 11, 2025Updated last year
- Minimal codebase for efficiently training Natural Language Autoencoders (NLAs). Built on Celeste's nanoNLA: https://github.com/ceselder/n…☆14Jul 10, 2026Updated 3 months ago
- A public-domain dataset of prompts and scenarios for evaluating compliance with the OpenAI Model Spec.☆17Mar 24, 2026Updated 7 months ago
- Zero-dependency local web app for browsing Claude Code session transcripts☆15Updated this week
- ☆91Feb 18, 2026Updated 8 months ago
- Tools for optimizing steering vectors in LLMs.☆22Apr 10, 2025Updated last year
- Automatically create Anki cards from text using language models☆20Jan 7, 2023Updated 3 years ago
- AlgZoo: uninterpreted models with fewer than 1,500 parameters☆63Aug 19, 2026Updated 2 months ago
- ☆20Apr 10, 2025Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- Benchmark dataset for evaluating trusted monitors on AI agent transcripts☆19May 16, 2026Updated 5 months ago
- AI Security Bootcamp public repository☆27Jul 2, 2026Updated 4 months ago
- ☆67Jul 4, 2025Updated last year
- Parameter Decomposition☆153Oct 20, 2026Updated last week
- ☆30Sep 3, 2025Updated last year
- ☆57Oct 23, 2023Updated 3 years ago
- Mamba support for transformer lens☆20Sep 17, 2024Updated 2 years ago
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- Code for Negation Neglect☆18May 22, 2026Updated 5 months ago
- 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.
- Coding agent skills for Inspect AI and its ecosystem☆18Sep 26, 2026Updated last month
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆21Jan 19, 2025Updated last year
- a metaprogramming language that compiles from types☆10Jun 26, 2024Updated 2 years ago
- A framework for testing and evaluating AI agents across various task domains, designed for misalignment interpretability research.☆35Sep 17, 2026Updated last month
- Training LLMs to Report Their Learned Behaviors☆30Apr 28, 2026Updated 6 months ago
- Einsum with einops style variable names☆19May 16, 2024Updated 2 years ago
- A curated reading list for researchers in the Philosophy of Interpretability☆21Aug 17, 2025Updated last year