INDEX

Explanations

author

np_max-act · gemini-2.0-flash

The neuron activates on the document metadata field indicating the “author” label.

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

fang

-0.06

.firstname

-0.06

 Ridley

-0.06

lek

-0.06

ndl

-0.06

 stripes

-0.06

 Colbert

-0.06

�

-0.06

 japon

-0.05

HttpGet

-0.05

POSITIVE LOGITS

�

0.07

+-

0.07

 vệ

0.07

 possessed

0.07

Under

0.07

 excluded

0.06

 groupId

0.06

_WEEK

0.06

Algorithm

0.06

/plain

0.06

Activations Density 0.001%

author

The neuron activates on the document metadata field indicating the “author” label.

No Comments

No Known Activations