INDEX

Explanations

surveys

np_max-act · gemini-2.0-flash

This neuron detects mentions of the number of questions or items in a survey or questionnaire instrument.

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

 replies

-0.07

 type

-0.07

fwrite

-0.07

 mond

-0.07

shirt

-0.07

 Output

-0.06

 así

-0.06

:class

-0.06

 fwrite

-0.06

 float

-0.06

POSITIVE LOGITS

 İnsan

0.08

venge

0.07

九

0.07

 tổn

0.06

 अगर

0.06

ترة

0.06

(DialogInterface

0.06

산업

0.06

_DEAD

0.06

іки

0.06

Activations Density 0.020%

surveys

This neuron detects mentions of the number of questions or items in a survey or questionnaire instrument.

No Comments

No Known Activations