INDEX

Explanations

Gallery

np_max-act · gemini-2.0-flash

The neuron mainly detects occurrences of the word “gallery” (or very close variants) as a heading or label.

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

 restart

-0.07

됨

-0.07

 McCain

-0.07

Nd

-0.06

(comp

-0.06

hread

-0.06

.Enc

-0.06

 Mund

-0.06

 setup

-0.06

 Backup

-0.06

POSITIVE LOGITS

 Gallery

0.11

 gallery

0.10

 galleries

0.09

 galer

0.08

.gallery

0.08

 гал

0.08

 Gall

0.08

arry

0.08

гал

0.07

 Gallagher

0.07

Activations Density 0.003%

Gallery

The neuron mainly detects occurrences of the word “gallery” (or very close variants) as a heading or label.

No Comments

No Known Activations