INDEX

Explanations

Legal documents

np_max-act · gemini-2.0-flash

This neuron activates on mentions of legal filings and court-related documents (e.g., court, affidavit, complaint, charging documents).

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

mist

-0.08

 Vish

-0.07

 Archbishop

-0.06

_qos

-0.06

meni

-0.06

 Citizen

-0.06

 poisonous

-0.06

'>"+

-0.06

Bag

-0.06

routeProvider

-0.06

POSITIVE LOGITS

 stranger

0.06

 그의

0.06

ups

0.06

ijken

0.06

 prostor

0.06

(d

0.06

ươ

0.06

 Diğer

0.06

 Mojo

0.06

 tasks

0.06

Activations Density 0.007%

Legal documents

This neuron activates on mentions of legal filings and court-related documents (e.g., court, affidavit, complaint, charging documents).

No Comments

No Known Activations