Vannus records that this vendor routes across several model providers — not captured by one. Every finding below is quoted to the vendor’s own document, or marked not disclosed where the vendor publishes nothing.
Open-source Python library for representation engineering — extracts control vectors from model activations and applies them to steer LLM behaviour at inference time.
Our RepReading and RepControl pipelines inherit the 🤗 Hugging Face pipelines for both classification and generation.
The quote above names one provider. The multi-provider finding rests on the vendor’s full disclosure — None shipped — instruments whichever Hugging Face model the caller passes into the pipeline — not on that line alone.
Not yet assessed. We publish a sovereignty position only where the vendor documents one — we do not infer it from a domain or a company name.
Vannus records, from the vendor's own published documents, the legal entity a customer contracts with, the country that entity sits in, and the governing law of its terms — and whether the vendor runs its own model or resells someone else's. Each finding is quoted to its source and dated, or marked not disclosed where the vendor publishes nothing. No paid placement on a record, in the catalog or in search — affiliate status is walled off from the record, enforced by a test in the build. See the methodology →