INDEX

Explanations

legal arguments

np_max-act · gemini-2.0-flash

This neuron activates on legal‐document reference markers—i.e. statute and case citations, section numbers, docket numbers, and similar formal legal references.

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

TG

-0.07

end

-0.07

Facade

-0.07

 come

-0.06

/memory

-0.06

 Morgan

-0.06

WARDED

-0.06

ourmet

-0.06

 rugby

-0.06

GridLayout

-0.06

POSITIVE LOGITS

0.07

şehir

0.06

Benef

0.06

uro

0.06

'{"

0.06

 zvyš

0.06

BIO

0.06

<User

0.06

诗

0.06

Pek

0.06

Activations Density 0.015%

legal arguments

This neuron activates on legal‐document reference markers—i.e. statute and case citations, section numbers, docket numbers, and similar formal legal references.

No Comments

No Known Activations

legal arguments

This neuron activates on legal‐document reference markers—i.e. statute and case citations, section numbers, docket numbers, and similar formal legal references.

No Comments

No Known Activations