INDEX

Explanations

activity

np_max-act · gemini-2.0-flash

The neuron triggers on Android manifest XML element names—especially component declarations like `<activity>` (and related tags such as `<intent-filter>`).

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

enet

-0.06

ýš

-0.06

fon

-0.06

lichen

-0.06

_dict

-0.06

 Orwell

-0.06

 리스트

-0.06

 ylim

-0.06

 podstat

-0.05

 BorderRadius

-0.05

POSITIVE LOGITS

_WH

0.07

-total

0.07

Vac

0.07

(blog

0.07

ocomplete

0.07

 Ultra

0.07

 Blob

0.06

(Device

0.06

革

0.06

itest

0.06

Activations Density 0.001%

activity

The neuron triggers on Android manifest XML element names—especially component declarations like `<activity>` (and related tags such as `<intent-filter>`).

No Comments

No Known Activations