6 citations · 6 across the 3 of their papers we have counts for
3 papers
Decomposing Refusal Steering in Mixture-of-Experts Models
Anna C. Marbut, Daniel R. Olson, Travis J. Wheeler
Safety alignment in instruction-tuned large language models (LLMs) depends on a model's ability to reliably refuse harmful or disallowed requests. Recent work has shown that a stee…
Reliable Measures of Spread in High Dimensional Latent Spaces
Anna C. Marbut, Katy McKinney-Bock, Travis J. Wheeler
Understanding geometric properties of natural language processing models' latent spaces allows the manipulation of these properties for improved performance on downstream tasks. On…
SODA: a TypeScript/JavaScript Library for Visualizing Biological Sequence Annotation
Jack W. Roddy, George T. Lesica, Travis J. Wheeler
We present SODA, a lightweight and open-source visualization library for biological sequence annotations that enables straightforward development of flexible, dynamic, and interact…