INDEX

Explanations

interest

np_max-act · gemini-2.0-flash

The neuron is sensitive to “conflict of interest” disclosures in the text.

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

建

-0.07

FirstChild

-0.06

.RichTextBox

-0.06

/**

-0.06

 nick

-0.06

 GroupLayout

-0.06

 snippet

-0.06

 peptides

-0.06

 bulk

-0.06

 CAPITAL

-0.06

POSITIVE LOGITS

 спе

0.07

�

0.07

 stellar

0.07

فع

0.07

선거

0.06

 ekonomik

0.06

º

0.06

masters

0.06

FALSE

0.06

SST

0.06

Activations Density 0.001%

interest

The neuron is sensitive to “conflict of interest” disclosures in the text.

No Comments

No Known Activations

interest

The neuron is sensitive to “conflict of interest” disclosures in the text.

No Comments

No Known Activations