INDEX

Explanations

aperture values

np_max-act · gemini-2.0-flash

The neuron activates on numerical tokens in camera lens specifications—particularly focal-length (mm) and aperture (f/…) values.

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

Employ

-0.07

 Detection

-0.07

 formato

-0.07

 gioc

-0.07

zw

-0.06

fis

-0.06

El

-0.06

 ding

-0.06

-med

-0.06

 parece

-0.06

POSITIVE LOGITS

 chóng

0.07

.sigma

0.07

 کنید

0.07

ertainment

0.07

 ActivityCompat

0.07

.MODE

0.07

هر

0.06

.facebook

0.06

 improves

0.06

्सर

0.06

Activations Density 0.001%

aperture values

The neuron activates on numerical tokens in camera lens specifications—particularly focal-length (mm) and aperture (f/…) values.

No Comments

No Known Activations