INDEX

Explanations

AP

np_max-act · gemini-2.0-flash

This neuron detects the formal header of a Fourth Circuit U.S. Court of Appeals opinion, especially the words in “United States Court of Appeals for the Fourth Circuit.”

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

‌تواند

-0.07

Larry

-0.07

 کشور

-0.07

_tC

-0.07

Jur

-0.07

 Larry

-0.06

 jsme

-0.06

_handling

-0.06

Jerry

-0.06

home

-0.06

POSITIVE LOGITS

 elektrik

0.07

 Million

0.06

ニメ

0.06

 specifications

0.06

fef

0.06

 traditions

0.06

ーー

0.06

(im

0.06

at

0.06

뮤

0.06

Activations Density 0.004%

AP

This neuron detects the formal header of a Fourth Circuit U.S. Court of Appeals opinion, especially the words in “United States Court of Appeals for the Fourth Circuit.”

No Comments

No Known Activations