INDEX

Explanations

Inform

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zz

-0.07

Bey

-0.07

 пы

-0.07

�

-0.07

 capacity

-0.07

 switching

-0.06

_j

-0.06

 capabilities

-0.06

 slavery

-0.06

zs

-0.06

POSITIVE LOGITS

 inform

0.14

 Inform

0.13

Inform

0.12

 informant

0.11

 informed

0.11

inform

0.11

 informing

0.10

 informative

0.09

informatics

0.08

 informs

0.08

Activations Density 0.017%

Inform

No Comments

No Known Activations