INDEX

Explanations

ant

np_max-act · gemini-2.0-flash

The neuron mainly fires on long, domain-specific scientific or biomedical jargon terms (e.g., “antigens,” “dendritic,” “costimulatory receptors,” “micrometers,” “generative,” etc.).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 subsequently

-0.07

 impe

-0.07

 кін

-0.07

(fid

-0.06

 just

-0.06

 그냥

-0.06

 Buck

-0.06

 Truman

-0.06

_BS

-0.06

 bilgi

-0.06

POSITIVE LOGITS

ในว

0.06

よりも

0.06

ียว

0.06

 zona

0.06

utut

0.06

 jeux

0.06

Around

0.06

 суд

0.06

 essentials

0.06

 zveřej

0.06

Activations Density 0.740%

ant

The neuron mainly fires on long, domain-specific scientific or biomedical jargon terms (e.g., “antigens,” “dendritic,” “costimulatory receptors,” “micrometers,” “generative,” etc.).

No Comments

No Known Activations