INDEX

Explanations

Aut

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 rich

-0.07

.List

-0.07

 king

-0.06

 pocit

-0.06

 ряд

-0.06

 gris

-0.06

 kinds

-0.06

 show

-0.06

 preview

-0.06

 render

-0.06

POSITIVE LOGITS

Aut

0.12

au

0.11

aut

0.10

 Auto

0.10

.aut

0.10

aut

0.09

’aut

0.09

AUT

0.09

'aut

0.09

AU

0.09

Activations Density 0.041%

Aut

No Comments

No Known Activations