ENTITY
Activation Outliers
Activation Outliers
PulseAugur coverage of Activation Outliers — every cluster mentioning Activation Outliers across labs, papers, and developer communities, ranked by signal.
Total · 30d
1
2 over 90d
Releases · 30d
0
0 over 90d
Papers · 30d
1
2 over 90d
TIER MIX · 90D
TOPICS
SENTIMENT · 30D
1 day(s) with sentiment data
RECENT · PAGE 1/1 · 2 TOTAL
-
Native low-bit LLM architectures outperform post-training compression
The article argues that post-training compression techniques for large language models are fundamentally flawed. It explains that these methods, which attempt to reduce model size by quantizing weights after training, f…
-
New SAE methods enhance interpretability and stability
Researchers have introduced several advancements in Sparse Autoencoders (SAEs) to improve their interpretability and stability. Concept-SAE offers a controllable interface for probing user-defined concepts within SAEs, …