INDEX

Explanations

convincing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_3/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

tréal

-0.06

 прох

-0.06

BOOLE

-0.06

UM

-0.06

antee

-0.06

 merc

-0.06

_PERIOD

-0.06

∈

-0.06

_platform

-0.06

POSITIVE LOGITS

 convincing

0.29

 compelling

0.11

 believable

0.09

 convinc

0.09

 conviction

0.07

Their

0.07

접

0.07

ller

0.06

ITION

0.06

.Department

0.06

Activations Density 0.003%

convincing

No Comments

No Known Activations