INDEX

Explanations

Advertisements/listings

np_max-act · gemini-2.0-flash

This neuron activates on listing-style numeric and measurement tokens (years, dimensions, counts, prices, fractions) found in property or product descriptions.

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

sharing

-0.07

、や

-0.07

backgroundColor

-0.07

'));↵↵

-0.07

gas

-0.06

tep

-0.06

PROFILE

-0.06

TouchableOpacity

-0.06

 logos

-0.06

 behavior

-0.06

POSITIVE LOGITS

ağı

0.07

 пораж

0.06

 провести

0.06

 statt

0.06

 skvěl

0.06

матрива

0.06

ACM

0.06

 болезни

0.06

И

0.06

 přátel

0.06

Activations Density 0.019%

Advertisements/listings

This neuron activates on listing-style numeric and measurement tokens (years, dimensions, counts, prices, fractions) found in property or product descriptions.

No Comments

No Known Activations