INDEX

Explanations

attack

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

 озна

-0.07

 symbol

-0.07

 persuaded

-0.06

 basis

-0.06

 eşit

-0.06

-income

-0.06

 mobil

-0.06

Zá

-0.05

POSITIVE LOGITS

 attack

0.19

 attacks

0.18

 Attack

0.18

 attacked

0.17

 attacking

0.15

 Attacks

0.14

 ATTACK

0.14

attack

0.13

Attack

0.10

 assault

0.10

Activations Density 0.020%

attack

No Comments

No Known Activations