INDEX

Explanations

duration

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 WHITE

-0.07

[key

-0.07

Lake

-0.07

Yet

-0.07

 pick

-0.06

 George

-0.06

 picks

-0.06

robots

-0.06

White

-0.06

 enemies

-0.06

POSITIVE LOGITS

 duration

0.13

duration

0.10

Duration

0.10

Dur

0.10

 Duration

0.09

UR

0.09

-duration

0.09

WithDuration

0.09

_dur

0.09

_duration

0.08

Activations Density 0.012%

duration

No Comments

No Known Activations