INDEX

Explanations

preferences/settings

np_max-act · gemini-2.0-flash

The neuron fires on mentions of configuring or changing application settings—especially menu paths, preferences, and “Settings” instructions.

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

_chars

-0.08

 sandwich

-0.07

.disabled

-0.06

 Mull

-0.06

Bh

-0.06

agnostics

-0.06

(buffer

-0.06

)&&(

-0.06

 systemctl

-0.06

 modifiers

-0.06

POSITIVE LOGITS

αιν

0.07

.LOC

0.06

лем

0.06

ruta

0.06

 사진

0.06

ranking

0.06

 Rakou

0.06

 blurry

0.06

ظٹط

0.06

 constexpr

0.06

Activations Density 0.045%

preferences/settings

The neuron fires on mentions of configuring or changing application settings—especially menu paths, preferences, and “Settings” instructions.

No Comments

No Known Activations