INDEX

Explanations

final

np_max-act · gemini-2.0-flash

This neuron detects mentions of “final” in connection with court dispositions (e.g. final judgment/order/decision).

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

 geographic

-0.07

 validations

-0.07

 ابزار

-0.07

(Local

-0.07

 controls

-0.07

 prolet

-0.07

 nước

-0.07

 decoder

-0.07

Escort

-0.06

 replaced

-0.06

POSITIVE LOGITS

0.07

ALLEL

0.06

pectives

0.06

�

0.06

min

0.06

.Popen

0.06

₃

0.06

 fruition

0.06

 Cruz

0.06

čas

0.06

Activations Density 0.001%

final

This neuron detects mentions of “final” in connection with court dispositions (e.g. final judgment/order/decision).

No Comments

No Known Activations