Goodfire @GoodfireAI

interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works already-clean.goodfire.com

@shlok_ch on it 🫡

We identified a gene variant behind hearing loss, a big step for interpretability in medicine. In April, our interpretability system EVEE scored all 4.2M variants in ClinVar, the NIH's variant database. MEPE c.209_212del scored particularly high, so we built a case and had it successfully reclassified as "likely pathogenic." ~2M variants are still "uncertain," but we believe interpretability can help us understand many more!

The variant: ncbi.nlm.nih.gov/clinvar/variat… How we made EVEE: goodfire.com/research/evee-…

AI can explain its reasoning. That doesn’t mean we know how it made the decision. @GoodfireAI co-founder and chief scientist @banburismus_ joins Rocket Drew to explore what AI “brain scans” could reveal that written reasoning misses. 🚀 Watch AI Deep Dive on YouTube: thein.fo/3VJTpzl Spotify: thein.fo/4e6QSp8

🚀 AI Deep Dive Episode 5: Can We See Inside an AI’s Mind? AI can write down its reasoning. But what happens when more of its thinking never makes it onto the page? @rocketalignment and @GoodfireAI co-founder and chief scientist Tom McGrath explore what AI “brain scans” can reveal beyond written reasoning, how internal signals could help catch cheating, and what it would take to understand—and change—what models learn. 00:00 Intro 00:39 Tom McGrath and AI brain scans 09:01 Written reasoning and hidden computation 17:45 Why AI is hard to understand 24:07 How researchers identify concepts 31:10 What interpretability could change 34:42 Reverse engineering a language model 43:09 The field’s approaches and investment 51:51 Changing models without hiding problems 1:00:10 AI agents studying AI

Teams can configure how their applications respond when a concern is flagged, including logging, additional review, refusal, and re-routing. If you serve or train models and want monitors built into your stack, learn more: goodfire.com/blog/goodfire-…

Our activation monitors detect undesired behaviors using signals from inside a model, so they catch more, run faster, and cost less than text-based monitors. Baseten customers can monitor for: - Prompt injection - Actions outside policy - Sensitive data exposure - Cyber misuse

Goodfire safety infrastructure 🤝 @baseten inference Today we're partnering with Baseten to bring real-time safety monitoring to open models. This is an important step toward our vision of ensuring every capable model has a frontier alignment stack.

Baseten @baseten

a week ago

Open models can come from anywhere. Securing them shouldn’t depend on where you get them. Today we're launching Project Beacon to make safety a default for open intelligence. We're partnering with @GoodfireAI to bring inference and in-line monitoring together for the first

7 18 124 25K 33

The Alzheimer’s Translation Challenge is led by @PrimaMente and @AlzData, with @nvidia, @huggingface, @nebiusai, Talisman Therapeutics, @UltimaGenomics, @cellanome, @PrimeIntellect, and @boltz_bio. Registration is open now. Competition starts spring 2027: primamente.com/challenges

Participants will use the dataset to build AI models, assessed through a series of evals from general benchmarks to more complex tasks. Top teams will be shortlisted, and their experimental hypotheses tested in Prima Mente's wet lab.

We discovered a new class of Alzheimer’s biomarkers with @PrimaMente. Today we're taking the next step by opening a global AI competition to discover new treatments. Introducing the Alzheimer’s Translation Challenge, led by @PrimaMente and @AlzData. 🧵

Read the full post: goodfire.com/research/produ… If you're interested in deploying these monitors, get in touch: goodfire.com/contact-us

Running the probes during inference maintains the same throughput with no added latency. That’s enabled by our infra engineering, like kernel-level optimizations and a custom inference server.

We built cybersecurity monitors for Kimi K3 and GLM 5.3 — more accurate, 50x faster, & 50x cheaper than an optimized LLM judge. External red-teaming from @farairesearch found that our monitor greatly reduces universal jailbreaks. 🧵

Happy hour RSVP: luma.com/timy2nh8

Tue 11am (Franciscan A) Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior Tue 4:30pm (Imperial Ballroom) Do SAEs Capture Concept Manifolds? Wed 4:30pm (Franciscan B) Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts

Manifold steering, SAE geometry, and a model that ignores its own clock…our researchers are at @COLM_conf this week to present papers on all three. Meet them at our booth, Tue-Thu, 1:30-2:30pm. Poster times and happy hour RSVP below 👇