Neuron Atlas - Goodfire
Presents an interactive Goodfire tool for exploring language model neurons through overviews, mode landscapes and circuits; the abstract gives no explicit safety motivation.
Research
Goodfire
Understanding and steering neural networks. goodfire.com
Focus All
Topic Interpretability
Source Goodfire · 16
Date Past 6 months
2 items
Neurons as an Interpretable Basis
Argues that SwiGLU MLP neurons in language models are sparse, concisely describable, and predictable units of computation, and builds subcircuit and mode analyses plus automated neuron descriptions.
1 item
Shaping and Monitoring Models Through Their Internal Representations
Introduces mechanistic shaping, which trains models through their internal representations to be right for the right reasons, reducing sycophancy, reward hacking and confounder use, and studies effects on monitorability.
1 item
Neural Networks Are Already Clean
Argues that polysemanticity and superposition were misread as arbitrary packing, that networks' own neurons and circuits are legible, and that mechanistic interpretability is more tractable than feared.
1 item
Accelerating Interpretability: A Human Genome Project for AI
Goodfire essay proposing a cross-industry "Human Genome Project for AI" to reverse-engineer frontier LLMs, using agentic experiment-running to scale interpretability research for understanding and aligning AI.
1 item
Goodfire and Baseten partner to bring frontier safety to open models
Goodfire and Baseten announce Project Beacon, deploying white-box activation monitors to detect unsafe agentic behaviour in open models in real time, cutting judge costs about 50x.
1 item
Training and Deploying Production Cyber Monitors on Kimi K3
Builds probe-based cybersecurity monitors for Kimi K3 and GLM 5.3 that flag suspicious agent exchanges for an LLM judge, matching its recall at about 50x lower cost.
1 item
We can and must solve alignment
Goodfire argues that interpretability is the bottleneck for technical alignment and outlines its plan to understand, monitor, and shape model behaviour.
1 item
A practical guide to sparse autoencoders (SAEs)
A practical guide explaining what sparse autoencoders are useful for, when to use probes or other alternatives, and how to train a good SAE on a model.
1 item
Models know when they’re reward hacking — and we can catch them at scale
Goodfire finds models have an internal signal accompanying reward hacking, and trains activation probes that detect it in real time, outperforming chain-of-thought monitors.
1 item
How to build fast, efficient monitors for AI models using probes
An introductory guide to activation probes as low-latency monitors that read model internals to detect unsafe agent behaviour, covering when and how to build them.
1 item
Announcing Goodfire Research Grants
Goodfire announces $1M in free access to its interpretability agent Silico for academic and nonprofit labs working on interpretability, alignment and safety. It is a funding announcement, not a research result.
1 item
Uncovering Neural Geometry in Vision Models With Block-Sparse Featurizers
Introduces Block-Sparse Featurizers that decompose vision model activations into multidimensional subspaces, finding more parsimonious interpretable features that enable fine-grained steering.
1 item
Meandering on Manifolds: The Neural Geometry of Stories Over Time
Studies how LLM activations trace trajectories on emotion manifolds as they read stories sentence by sentence, combining static geometry with temporal dynamics. Interpretability work with no explicit safety motivation.
1 item
Can SAEs Capture Neural Geometry?
Shows that sparse autoencoder features capture curved neural manifolds only partially, identifies three ways lines represent curves, and proposes an unsupervised pipeline for discovering concept manifolds.
1 item
A Geometric Calculator Inside a Neural Network
Goodfire finds Llama 3.1 8B uses a general-purpose addition module operating on circular Fourier representations of numbers, reused across addition-like tasks. The work is not safety-motivated.