INDEX

Explanations

in

np_max-act · gemini-2.0-flash

This neuron detects passive-voice occurrences of medical findings or complications being present or developing in a specified number of cases.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 норматив

-0.07

 Newspaper

-0.06

 gusto

-0.06

ass

-0.06

GetInt

-0.06

 Reward

-0.06

_NETWORK

-0.06

ประสบ

-0.06

 Giám

-0.06

Tomorrow

-0.06

POSITIVE LOGITS

 понад

0.07

÷

0.07

 châu

0.07

ή

0.06

Ü

0.06

 dahil

0.06

//@

0.06

Empty

0.06

 mName

0.06

قال

0.06

Activations Density 0.024%

in

This neuron detects passive-voice occurrences of medical findings or complications being present or developing in a specified number of cases.

No Comments

No Known Activations