INDEX

Explanations

vote

np_max-act · gemini-2.0-flash

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

_area

-0.08

 TECH

-0.07

 companies

-0.07

LAND

-0.07

 cleaning

-0.07

 specimen

-0.07

 acquired

-0.07

 discovered

-0.06

 LaTeX

-0.06

 explorer

-0.06

POSITIVE LOGITS

 voting

0.14

 Vote

0.14

 vote

0.13

 votes

0.12

Vote

0.11

_vote

0.11

vote

0.10

 voted

0.10

 Voting

0.10

 voter

0.10

Activations Density 0.013%

vote

No Comments

No Known Activations

vote

No Comments

No Known Activations