LoreonLabsPlatform

Overview

Intelligence

Markets
Builders
Research
Narratives
Ecosystems
Launchpads

Discover

Search
Sources

Builder

Callum McDougall

Interpretability Researcher at Google DeepMind. ex-director of the ARENA program.

Followers

442

Public repos

32

Stars (recent)

1.8K

Ecosystems

1

Projects

Repositories this builder owns.

No description.

No description.

5

Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

arena-llm-context

Useful source of context (github repos & research papers / blog posts) for LLMs while working on ARENA.

Connected narratives

AI Agents Consumer Crypto SocialFi Stablecoins Agent Commerce Onchain Apps

Related builders

Others building in the same ecosystem.

arena-pragmatic-interp

No description.

computational-thread-art-v3

No description.

computational-thread-art

Code that renders an image as a series of lines connecting pins around a circular frame (for more detail, see my Medium page).

Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.

Recent activity

Most recently pushed work.

callummcdougall/ARENA_3.0
pushed 1d ago
callummcdougall/arena-heroku
pushed 7d ago
callummcdougall/sae_vis
pushed 4mo ago
callummcdougall/arena-llm-context
pushed 4mo ago