Steer AI by Ramp Labs
labs.ramp.com · 178 words · saved by 1 readers
Build and chat with activation-steered AI personalities trained on Modal.
A large language model processes text as vectors flowing through dozens of transformer layers. Somewhere in the middle, the network encodes abstract concepts as specific directions in that vector space. Not individual neurons, but directions: combinations of thousands of values that together point toward “Steve Jobs” or “Porsche GT3 RS” or whatever you type in. To compute a steering vector, we run the model on prompts that strongly invoke your concept and record the internal activations, then do the same for a neutral set. The difference between those two averages is the steering vector: a…
saved by
related reading
- AI Platform for Accounting Firms | Ramp Stackramp.com
- Router by Ramprouter.com
- Activation Steering in 2026: A Practitioner's Field Guide | Subhadip Mitrasubhadipmitra.com
- Steering GPT-2-XL by adding an activation vector — AI Alignment Forumalignmentforum.org
- [2605.03907] Steer Like the LLM: Activation Steering that Mimics Promptingarxiv.org
- Steering Might Stop Working Soon — LessWronglesswrong.com
- Introducing System One Models & Jev - TypeSafe AI Blogtypesafe.ai
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- Dreaming Vectors: Gradient-descented steering vectors from Activation Oracles and using them to Red-Team AOs — LessWronglesswrong.com
- Automated Weak-to-Strong Researcheralignment.anthropic.com
- Mechanistically Eliciting Latent Behaviors in Language Models — AI Alignment Forumalignmentforum.org
- Thinking like Transformersrush.github.io