INDEX

Explanations

are

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

 Tank

-0.07

 queens

-0.06

 کو

-0.06

 skateboard

-0.06

ます

-0.06

-,

-0.06

ads

-0.06

Cash

-0.06

.Agent

-0.06

RTE

-0.06

POSITIVE LOGITS

 distancia

0.08

 Scalars

0.07

 succesfully

0.07

 evaluated

0.07

 Flor

0.07

 doubtful

0.07

 Formatting

0.07

 otevř

0.06

\Models

0.06

normally

0.06

Activations Density 0.000%

are

No Comments

No Known Activations