A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.

Entropy Based Sampling and Parallel CoT Decoding

Local CLIP search over meme libraries

A language model programming library.

Instant is a modern Firebase. We make you productive by giving your frontend a real-time database.

zoomable chart with brush made with shadcn charts / recharts