4 papers
Harmful Intent as a Geometrically Recoverable Feature of LLM Residual Streams
Isaac Llorente-Saguer
Aligned language models refuse harmful instructions, but the representations through which they recognise such instructions are less well characterised than the behaviours they pro…
The Geometry of Harmful Intent: Training-Free Anomaly Detection via Angular Deviation in LLM Residual Streams
Isaac Llorente-Saguer
We present LatentBiopsy, a training-free method for detecting harmful prompts by analysing the geometry of residual-stream activations in large language models. Given 200 safe norm…
A Lock-Free, Fully GPU-Resident Architecture for the Verification of Goldbach's Conjecture
Isaac Llorente-Saguer
We present a fully device-resident, multi-GPU architecture for the large-scale computational verification of Goldbach's conjecture. In prior work, a segmented double-sieve eliminat…
GoldbachGPU: An Open Source GPU-Accelerated Framework for Verification of Goldbach's Conjecture
Isaac Llorente-Saguer
We present GoldbachGPU, an open-source framework for large-scale computational verification of Goldbach's conjecture using commodity GPU hardware. Prior GPU-based approaches report…