INDEX

Explanations

names

np_max-act · gemini-2.0-flash

The neuron activates on capitalized personal names (i.e. proper first names) in the text.

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

 cultural

-0.07

 Nuggets

-0.07

 british

-0.06

 sticky

-0.06

 exploded

-0.06

|l

-0.06

wendung

-0.06

Procedure

-0.06

	fprintf

-0.06

 borderline

-0.06

POSITIVE LOGITS

タイ

0.07

_HandleTypeDef

0.06

 eBooks

0.06

PF

0.06

ータ

0.06

-fe

0.06

bek

0.06

abee

0.06

 пищ

0.06

Activations Density 0.045%

names

The neuron activates on capitalized personal names (i.e. proper first names) in the text.

No Comments

No Known Activations

names

The neuron activates on capitalized personal names (i.e. proper first names) in the text.

No Comments

No Known Activations