INDEX

Explanations

legal claims

np_max-act · gemini-2.0-flash

This neuron detects formal legal‐procedure terms (e.g. “hear,” “case,” “claim,” “jurisdiction”).

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

 described

-0.06

고

-0.06

 dances

-0.06

_tC

-0.06

฿

-0.06

 opened

-0.06

 خر

-0.06

 tình

-0.06

かった

-0.06

�

-0.06

POSITIVE LOGITS

ướng

0.07

PG

0.07

(Create

0.07

PG

0.07

acier

0.07

 hourly

0.06

MDB

0.06

\",\"

0.06

Collections

0.06

 сторін

0.06

Activations Density 0.014%

legal claims

This neuron detects formal legal‐procedure terms (e.g. “hear,” “case,” “claim,” “jurisdiction”).

No Comments

No Known Activations

legal claims

This neuron detects formal legal‐procedure terms (e.g. “hear,” “case,” “claim,” “jurisdiction”).

No Comments

No Known Activations