INDEX

Explanations

screen sizes, mobile views

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens—especially in responsive breakpoints or size/spacing specifications (e.g. screen widths, px values, sm/md/lg class prefixes).

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

 parental

-0.06

왔다

-0.06

 Krishna

-0.06

nm

-0.06

 granny

-0.06

Trans

-0.06

 Robot

-0.06

iber

-0.06

')");↵

-0.06

 Feed

-0.06

POSITIVE LOGITS

ửa

0.06

 Advanced

0.06

 getSupportFragmentManager

0.06

enerative

0.06

@Json

0.06

 glor

0.06

varchar

0.06

φαρ

0.06

 accents

0.05

.createUser

0.05

Activations Density 0.008%

screen sizes, mobile views

The neuron activates on numeric tokens—especially in responsive breakpoints or size/spacing specifications (e.g. screen widths, px values, sm/md/lg class prefixes).

No Comments

No Known Activations