INDEX

Explanations

plagiarism

np_max-act · gemini-2.0-flash

The neuron primarily detects mentions of plagiarism or plagiarism-detection contexts.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

terms related to plagiarism and academic integrity.

oai_token-act-pair · gpt-4o-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

rte

-0.07

 nests

-0.06

_reset

-0.06

구글상위

-0.06

TN

-0.05

-offset

-0.05

MMC

-0.05

イント

-0.05

"T

-0.05

_tree

-0.05

POSITIVE LOGITS

 plagiarism

0.08

 originated

0.08

اغ

0.07

 Contributor

0.07

物

0.07

 plagiar

0.07

!
↵

0.07

.Unknown

0.07

AGING

0.07

avia

0.07

Activations Density 0.002%

plagiarism

The neuron primarily detects mentions of plagiarism or plagiarism-detection contexts.

terms related to plagiarism and academic integrity.

No Comments

No Known Activations