INDEX

Explanations

page

np_max-act · gemini-2.0-flash

The neuron fires on instances of the word “page.”

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

 thus

-0.07

istrator

-0.07

-0.06

吹

-0.06

.enemy

-0.06

ToFit

-0.06

POSITIVE LOGITS

 page

0.14

 Page

0.14

page

0.13

Page

0.13

 pages

0.11

 pager

0.11

.page

0.10

pages

0.10

 daytime

0.10

.Page

0.10

Activations Density 0.037%

page

The neuron fires on instances of the word “page.”

No Comments

No Known Activations