INDEX

Explanations

code

np_max-act · gemini-2.0-flash

The neuron responds to occurrences of Angular Material component identifiers (i.e. tokens beginning with “mat-”).

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

ाम

-0.07

.dao

-0.07

되어

-0.06

 amet

-0.06

่อม

-0.06

(classes

-0.06

 ioctl

-0.06

ADDING

-0.06

ATAL

-0.06

济

-0.06

POSITIVE LOGITS

Ř

0.06

.Diagnostics

0.06

 東京

0.06

others

0.06

 Graves

0.06

*z

0.06

 Enhancement

0.06

 Poss

0.06

ख

0.06

'order

0.05

Activations Density 0.009%

code

The neuron responds to occurrences of Angular Material component identifiers (i.e. tokens beginning with “mat-”).

No Comments

No Known Activations