INDEX

Explanations

language and grammar

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Char

-0.07

nos

-0.06

dest

-0.06

 palabra

-0.06

 improving

-0.06

 preamble

-0.06

 estimate

-0.06

HK

-0.06

kir

-0.06

POSITIVE LOGITS

Thu

0.07

/set

0.07

 ReactiveFormsModule

0.07

ActiveSheet

0.06

 TextArea

0.06

.GetAxis

0.06

 "\">

0.06

.me

0.06

\Container

0.06

 BITTE

0.06

Activations Density 0.068%

language and grammar

No Comments

No Known Activations