INDEX

Explanations

before

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

 علي

-0.06

期間

-0.06

((&

-0.06

 Fate

-0.06

 Pharma

-0.06

 identify

-0.06

 된다

-0.06

협

-0.06

 Manchester

-0.06

 crater

-0.06

POSITIVE LOGITS

 Franken

0.07

MouseClicked

0.07

would

0.07

 lighting

0.06

 mundo

0.06

 would

0.06

_units

0.06

keypress

0.06

cock

0.06

 volleyball

0.06

Activations Density 0.000%

before

No Comments

No Known Activations