INDEX

Explanations

Minor

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

 learning

-0.07

creates

-0.07

 squeezing

-0.07

 creating

-0.06

.Download

-0.06

housing

-0.06

策

-0.06

 stimulation

-0.06

 satellite

-0.06

agination

-0.06

POSITIVE LOGITS

 minor

0.20

 Minor

0.17

Minor

0.14

 minors

0.10

minor

0.09

or

0.09

 menor

0.08

err

0.08

_minor

0.08

 petty

0.07

Activations Density 0.005%

Minor

No Comments

No Known Activations