INDEX

Explanations

shall

np_max-act · gemini-2.0-flash

This neuron detects legal‐style obligation markers, especially the modal verb “shall.”

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

 Breed

-0.07

 technolog

-0.07

genres

-0.07

upro

-0.07

ीप

-0.07

"G

-0.07

ผล

-0.07

منت

-0.07

子供

-0.06

اورپ

-0.06

POSITIVE LOGITS

 shall

0.14

 Shall

0.10

 SHALL

0.08

shall

0.07

 placements

0.07

will

0.07

setCellValue

0.07

hall

0.06

 Await

0.06

.setColumns

0.06

Activations Density 0.008%

shall

This neuron detects legal‐style obligation markers, especially the modal verb “shall.”

No Comments

No Known Activations