INDEX

Explanations

a

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

 autofocus

-0.07

.bt

-0.06

.Mapping

-0.06

 Coaching

-0.06

ázky

-0.06

 astore

-0.06

LET

-0.06

.xmlbeans

-0.06

POSITIVE LOGITS

 effect

0.07

 fingerprints

0.07

yl

0.06

 Prest

0.06

 merit

0.06

 conventional

0.06

 nature

0.06

ion

0.06

 emissions

0.06

 packageName

0.06

Activations Density 0.001%

a

No Comments

No Known Activations