INDEX

Explanations

App

np_max-act · gemini-2.0-flash

This neuron detects legal party-designation labels (e.g. “Appellant,” “Defendant–Appellant,” “Respondent,” etc.) in court‐case headers.

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

.Prot

-0.07

Riy

-0.07

�

-0.06

.On

-0.06

€↵

-0.06

.monitor

-0.06

detalle

-0.06

	UObject

-0.06

arde

-0.06

chnitt

-0.06

POSITIVE LOGITS

 gotten

0.06

(-

0.06

.setText

0.06

	distance

0.06

eligible

0.06

Hair

0.06

ribly

0.06

 hair

0.06

old

0.06

tabs

0.06

Activations Density 0.011%

App

This neuron detects legal party-designation labels (e.g. “Appellant,” “Defendant–Appellant,” “Respondent,” etc.) in court‐case headers.

No Comments

No Known Activations