The one-stop shop for LLM probes

See inside your model while it generates.

Runtime model monitoring with activation probes, starting with LLMs and video models. Catch risk during generation with our probes, or ones we train on your policy. For teams hosting their own open-weight or proprietary models.

Peer-reviewed at IEEE DSN-W 2026Peer-reviewed at IEEE Milcom 2026

Trusted by

NVIDIA Inception programPractical AI podcastOpen Secure AI AllianceThe Linux Foundation

How it works

The model already knows. We just read it.

1

Generation runs as normal.

The model processes the prompt and begins generating a response.

2

A probe reads the activation.

A small model (typically under 0.2% the size of the base model) inspects the internal state at inference time.

3

A risk score returns inline.

No separate guard model, no separate scanning pass — the signal is available before generation completes.

83–99% F1
WildJailbreak 99.1%, AEGIS 2.0 83.5%, BeaverTails 82.7% (Llama 3.1 8B)
See the benchmark details →
~550× smaller
A 12.6M-parameter probe vs. 7B guard models
<1ms
Probe runtime on LLMs, vs. 50–500ms generation

Peer-reviewed research

IEEE DSN-W 2026

Safety Beyond the Interface: Detecting Harm via Latent States in Large Language Models

We kept running into the same frustration with external guardrails: they're blind. They see tokens — what went in, what came out — but nothing in between. So we asked a simpler question: does the model already know when a prompt is harmful? We trained lightweight probes on LLaMA-3.1-8B's hidden states and found that it does — competitive with 7B guard models at a fraction of the cost.

IEEE Xplore
IEEE DSN-W 2026

Latent Space Probing for Adult Content Detection in Video Generative Models

Video generation models can be coaxed into producing explicit or harmful content with little effort. We trained lightweight probes on the internal latents of CogVideoX to detect unsafe content before a single pixel is decoded — competitive with 8B guard models at 500×+ lower latency.

IEEE Xplore (DOI)
IEEE Milcom 2026

Probing the Prefill: Detecting Code Vulnerabilities via Latent Activations

AI-generated code ships faster than anyone can review it. We asked whether a model's own hidden states, read at the moment it writes code, already carry a signal about whether that code is vulnerable — and trained lightweight probes on those latent activations to find out.

arXiv

Built for where safety matters most

LLM Safety

Flags harmful prompts and responses from a chatbot or assistant's own activations, without a separate guard model.

Learn more

AI Coding Tools

Early research: a coding model's activations carry a signal about vulnerable code. 68.8% best-case F1 and 41.7% on average, on labeled code, not yet live completions.

Learn more

Generative Video & Media

Probes on video diffusion models flag explicit content before a frame is decoded.

Learn more

See it on your own model

Use our probe-fitted models, or keep yours. Talk to us about running a pilot on your stack.

Talk to us