INDEX

Explanations

medical reports

np_max-act · gemini-2.0-flash

mentions that tests, imaging, or clinical findings are normal/negative or otherwise unremarkable.

oai_token-act-pair · gpt-5-mini

Triggered by @yooniel31

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

Negative Logits

 یون

-0.07

 #####

-0.06

ーパー

-0.06

LOOP

-0.06

(Array

-0.06

gu

-0.06

dirty

-0.06

 misled

-0.06

:len

-0.06

mpi

-0.06

POSITIVE LOGITS

_SIGNATURE

0.07

üm

0.06

.getSession

0.06

aus

0.06

TexImage

0.06

таб

0.06

vented

0.06

_display

0.06

yii

0.06

jar

0.06

Activations Density 0.034%

medical reports

mentions that tests, imaging, or clinical findings are normal/negative or otherwise unremarkable.

No Known Activations