INDEX

Explanations

court documents

np_max-act · gemini-2.0-flash

This neuron detects court docket headers—specifically the case‐number lines (e.g. “No. 14-1175”) and associated numeric identifiers in the opinion’s heading.

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

 Classes

-0.07

 fifth

-0.07

 Hour

-0.07

combo

-0.06

 assum

-0.06

оти

-0.06

.Mark

-0.06

кры

-0.06

ичної

-0.06

Utf

-0.06

POSITIVE LOGITS

 tehlik

0.07

 Yosemite

0.07

 τρα

0.06

&utm

0.06

톤

0.06

 Winston

0.06

 vị

0.06

 зміст

0.06

После

0.06

vider

0.06

Activations Density 0.010%

court documents

This neuron detects court docket headers—specifically the case‐number lines (e.g. “No. 14-1175”) and associated numeric identifiers in the opinion’s heading.

No Comments

No Known Activations