INDEX

Explanations

Geographic locations

np_max-act · gemini-2.0-flash

This neuron responds to numeric and measurement-related tokens (e.g. coordinates, area figures, population counts, percentages).

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

	game

-0.07

-0.06

 Hội

-0.06

 harga

-0.06

 PhoneNumber

-0.06

美国

-0.06

 replacements

-0.06

-sur

-0.06

人民共和国

-0.06

 RuntimeException

-0.06

POSITIVE LOGITS

0.06

 serr

0.06

 allele

0.06

ξ

0.06

 ruth

0.06

AZ

0.06

 smarty

0.06

uele

0.06

ीत

0.06

Activations Density 0.016%

Geographic locations

This neuron responds to numeric and measurement-related tokens (e.g. coordinates, area figures, population counts, percentages).

No Comments

No Known Activations