INDEX

Explanations

prejudicial

np_max-act · gemini-2.0-flash

This neuron detects substrings of legal‐procedural error terms—e.g. pieces of words like “mist-…-rial,” “prejud-…-icial,” “jury,” etc.—that appear in judicial opinions describing trial objections and motions.

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

Training

-0.07

 training

-0.06

 until

-0.06

рест

-0.06

ปล

-0.06

 Jean

-0.06

 reign

-0.06

video

-0.05

swers

-0.05

ileri

-0.05

POSITIVE LOGITS

 сегодня

0.07

ुबह

0.07

elleicht

0.06

="",

0.06

 Venez

0.06

 broad

0.06

 هي

0.06

 residence

0.06

%+

0.06

Activations Density 0.003%

prejudicial

This neuron detects substrings of legal‐procedural error terms—e.g. pieces of words like “mist-…-rial,” “prejud-…-icial,” “jury,” etc.—that appear in judicial opinions describing trial objections and motions.

No Comments

No Known Activations