INDEX

Explanations

administrative locations

np_max-act · gemini-2.0-flash

This neuron detects mentions of an administrative division’s “administrative center” (or seat).

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

_profile

-0.07

_cov

-0.06

าณ

-0.06

좀

-0.06

fr

-0.06

precio

-0.06

groups

-0.06

 patch

-0.06

edm

-0.06

ฟร

-0.06

POSITIVE LOGITS

ози

0.07

 créd

0.06

│

0.06

 JAXB

0.06

 Глав

0.06

 orang

0.06

 가지

0.06

 시즌

0.06

 sexually

0.06

Activations Density 0.006%

administrative locations

This neuron detects mentions of an administrative division’s “administrative center” (or seat).

No Comments

No Known Activations