INDEX

Explanations

0

np_max-act · gemini-2.0-flash

This neuron activates on floating-point numeric literals (decimal numbers) in the text.

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

Jay

-0.07

Uz

-0.06

Ral

-0.06

	text

-0.06

nuts

-0.06

Muk

-0.06

Bold

-0.06

Sentence

-0.06

_water

-0.06

θή

-0.06

POSITIVE LOGITS

 orientation

0.07

 posición

0.07

 PIXI

0.07

 priceless

0.07

 firepower

0.07

 forgot

0.07

 orientations

0.07

 Phòng

0.07

.P

0.07

 Patient

0.07

Activations Density 0.023%

0

This neuron activates on floating-point numeric literals (decimal numbers) in the text.

No Comments

No Known Activations