INDEX

Explanations

land

np_max-act · gemini-2.0-flash

This neuron spotlights floating-point numeric tokens (numbers with decimal points).

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

 Icon

-0.07

кор

-0.07

osaurs

-0.07

.website

-0.06

 Rigidbody

-0.06

 обст

-0.06

 Olson

-0.06

"('

-0.06

jul

-0.06

?).

-0.06

POSITIVE LOGITS

 land

0.11

土地

0.08

 lands

0.08

 mRNA

0.08

 patents

0.07

 Property

0.07

 земли

0.07

 inherited

0.07

 property

0.06

 Farmers

0.06

Activations Density 0.011%

land

This neuron spotlights floating-point numeric tokens (numbers with decimal points).

No Comments

No Known Activations

land

This neuron spotlights floating-point numeric tokens (numbers with decimal points).

No Comments

No Known Activations