INDEX

Explanations

R

np_max-act · gemini-2.0-flash

This neuron activates on Android resource‐reference tokens (e.g. R.layout…, R.id…, R.menu…, etc.).

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

дом

-0.07

＿

-0.07

 shouted

-0.07

timezone

-0.07

":"+

-0.06

-online

-0.06

(of

-0.06

 Auxiliary

-0.06

 Speak

-0.06

.wh

-0.06

POSITIVE LOGITS

precio

0.07

 використовувати

0.07

 отверсти

0.07

г

0.07

 căn

0.06

 tyres

0.06

 getC

0.06

IDS

0.06

.*,

0.06

態

0.06

Activations Density 0.002%

R

This neuron activates on Android resource‐reference tokens (e.g. R.layout…, R.id…, R.menu…, etc.).

No Comments

No Known Activations