Research / Knowledge Work
An LLM interpretability playground for forcing activations, exploring learned concepts, and comparing unmodified vs intervened generations.
The page clearly presents an AI-focused product with a specific use case: probing and intervening on LLM activations. The visible UI text explains the core workflows, including feature forcing, concept exploration, sampling controls, and side-by-side comparison of unmodified and intervened outputs. That gives enough evidence for a useful public listing.
The crawl does not show what model or SAE setup it uses, whether it supports uploads or only a fixed demo, or any documentation beyond basic in-page instructions. It’s also unclear how much of the feature browser is populated and whether the playground is fully usable from this snapshot.
Last evaluated 72 days ago. Current rank #2406. Down 1 spot in the rankings.
Primus is an autonomous AI researcher that hypothesizes, reads papers, writes code, runs experiments on compute, and drafts research papers. The page shows example tasks, published-paper claims, waitlist access, and positioning for ML research workflows.
An interactive dashboard that analyzes New York Times coverage since 2000 using the NYT Archive API, with views for reporters, beats, sections, subjects, geography, obituaries, and corrections.
A research article benchmarking bot detection systems against scripted browsers, stealth browsers, and modern AI browsing agents, with comparative results across five detection products.
An open benchmark and leaderboard for AI CAD agents, with 308 prompts across 20 categories and layered scoring for geometry, engineering, manufacturability, and cognition.
