INDEX

Explanations

Bi

np_max-act · gemini-2.0-flash

The neuron detects the “Bi” prefix in the “Biography” section headings of articles.

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

DY

-0.08

strong

-0.07

proved

-0.07

spaces

-0.07

 compelled

-0.07

_VECTOR

-0.06

_jobs

-0.06

此

-0.06

 elephants

-0.06

Watching

-0.06

POSITIVE LOGITS

зация

0.06

$↵↵

0.06

 `;↵

0.06

 Fahr

0.06

isches

0.06

ComputedStyle

0.06

íše

0.06

 FileSystem

0.06

alet

0.06

 دوباره

0.06

Activations Density 0.005%

Bi

The neuron detects the “Bi” prefix in the “Biography” section headings of articles.

No Comments

No Known Activations