INDEX

Explanations

poor

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

 adjective

-0.07

---------

-0.06

 practical

-0.06

 Testament

-0.06

 gang

-0.06

 escaping

-0.06

 excited

-0.06

--------

-0.06

 combinations

-0.06

adding

-0.06

POSITIVE LOGITS

 poor

0.17

 Poor

0.15

 poorly

0.14

Poor

0.10

èo

0.08

 poorest

0.08

opor

0.07

 Trou

0.07

贫

0.07

 başar

0.07

Activations Density 0.007%

poor

No Comments

No Known Activations