INDEX

Explanations

international

np_max-act · gemini-2.0-flash

The neuron activates on words signaling international or global contexts—e.g. mentions of “international,” “global,” or foreign scope.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

摩

-0.07

percent

-0.07

ทาง

-0.06

 decorate

-0.06

 enterprises

-0.06

แพ

-0.06

duk

-0.06

>tag

-0.06

商品

-0.06

POSITIVE LOGITS

getReference

0.08

.Checked

0.07

"))
↵

0.07

 UEFA

0.07

.closed

0.06

()))
↵

0.06

_out

0.06

.latest

0.06

")),

0.06

張

0.06

Activations Density 0.072%

international

The neuron activates on words signaling international or global contexts—e.g. mentions of “international,” “global,” or foreign scope.

No Comments

No Known Activations