INDEX

Explanations

Beijing

np_max-act · gemini-2.0-flash

This neuron specifically detects the token “Beijing.”

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

orphic

-0.08

cut

-0.07

 programme

-0.07

>{"

-0.07

 forest

-0.07

Cube

-0.06

 Rican

-0.06

 varied

-0.06

(HttpContext

-0.06

 Albania

-0.06

POSITIVE LOGITS

 Beijing

0.11

北京

0.09

 Tokyo

0.09

 北京

0.08

 Delhi

0.07

ęk

0.07

 Moscow

0.07

kez

0.07

ikh

0.07

Activations Density 0.012%

Beijing

This neuron specifically detects the token “Beijing.”

No Comments

No Known Activations