INDEX

Explanations

drive

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.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

 speculated

-0.07

 texture

-0.06

zá

-0.06

 successor

-0.06

 palace

-0.06

tag

-0.06

benh

-0.06

 rectangle

-0.06

 bbox

-0.06

POSITIVE LOGITS

 driven

0.10

驾

0.10

 drive

0.09

Driving

0.09

Drive

0.09

wi

0.08

بری

0.08

-driven

0.08

 Drive

0.08

 URLWithString

0.08

Activations Density 0.034%

drive

No Comments

No Known Activations