INDEX

Explanations

external

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

 ItemType

-0.07

 cycle

-0.07

 note

-0.07

 coins

-0.07

-per

-0.07

 rich

-0.07

 ducks

-0.07

aj

-0.07

-0.06

 Prep

-0.06

POSITIVE LOGITS

 external

0.15

 External

0.12

external

0.12

 externally

0.11

External

0.10

_external

0.10

extern

0.10

 extern

0.09

.external

0.09

EXTERNAL

0.08

Activations Density 0.015%

external

No Comments

No Known Activations