CuE: Activating and Suppressing Cultural Info in LLMs
simi_97k · x · 2026-07-12
Introduces the composition of Cultural Embeddings (CuE). Using Neuronpedia, the research team analyzed the sparse autoencoder features of the Gemma-2-9B model, discovering that cultural information within the model is shared, activated, and suppressed in an interpretable manner.
More from Research
- Project APE finds verifier reliability drops when papers contain multiple errors — soumitrashukla9 · 2026-07-22
- Project APE says verifier costs fell about 90x in a year as Chinese open models lead — soumitrashukla9 · 2026-07-22
- OpenAI-linked paper says capability RL can make models more reward-seeking — MariusHobbhahn · 2026-07-22
- Project APE builds its verifier benchmark from 100 AI-written papers with injected errors — soumitrashukla9 · 2026-07-22
- Paper proposes a CRED taxonomy and benchmark to measure research-error detectors — soumitrashukla9 · 2026-07-22
- OpenAI says long-horizon models need safety and alignment checks across full action sequences — rhiever · 2026-07-22