INDEX

Explanations

computer window settings

np_max-act · gemini-2.0-flash

The neuron activates on mentions of making a GUI window “always on top” or setting it as a topmost window.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Portrait

-0.06

атков

-0.06

anth

-0.06

_epsilon

-0.06

 insect

-0.06

 Alison

-0.06

 giàu

-0.06

 osobních

-0.06

umptech

-0.06

 Municipal

-0.06

POSITIVE LOGITS

 exhibiting

0.07

?action

0.06

_delay

0.06

-gay

0.06

 Underground

0.06

 Float

0.06

方式

0.06

lag

0.06

 Rach

0.06

?“

0.06

Activations Density 0.020%

computer window settings

The neuron activates on mentions of making a GUI window “always on top” or setting it as a topmost window.

No Comments

No Known Activations