INDEX

Explanations

control

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 resurrection

-0.07

 caller

-0.07

 Original

-0.07

onders

-0.07

enties

-0.06

 baik

-0.06

 sürec

-0.06

 cabe

-0.06

ﾞ

-0.06

 sauna

-0.06

POSITIVE LOGITS

 controlled

0.12

 Control

0.11

 control

0.10

controlled

0.09

Control

0.08

 Controlled

0.08

-controlled

0.08

 controlling

0.08

 контроль

0.08

control

0.08

Activations Density 0.069%

control

No Comments

No Known Activations