Author

Orion Reblitz-Richardson

Distiller Labs

h-index 5 Homepage View on Semantic Scholar

We have 2 of 11 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

Output Dilution: Redundant but Fragile Representations in MoE Models

Mixture-of-Experts (MoE) models appear to encode moral content as robustly as dense models, yet prove far more fragile in their encoding. In OLMoE-1B-7B, linear probes recover moral valence from nearly every expert-layer combination, with mean peak-layer accuracy above 90%. But these representations collapse under leve...

Orion Reblitz-Richardson · 1 citation

#natural language process... Preprint Aug 2026

How Language Models Organize and Structure Moral Knowledge

This work trains six independent linear probes on open-weight language models, one per Moral Foundations Theory (MFT) category, and examines how the resulting directions relate to each other in representation space, finding the directions neither collapse into a single moral detector nor isolate from one another.

Orion Reblitz-Richardson · 1 citation