INDEX

Explanations

Family relations

np_max-act · gemini-2.0-flash

The neuron fires on kinship and family-relation terms (e.g. father, mother, brother, sister, grand-, nephew, etc.).

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

 Podcast

-0.07

 detox

-0.07

첨부

-0.06

 Effective

-0.06

vid

-0.06

Opt

-0.06

 Entre

-0.06

Ils

-0.06

 Speedway

-0.06

&A

-0.06

POSITIVE LOGITS

زاده

0.07

 accommod

0.06

plat

0.06

弥

0.06

्�

0.06

 празд

0.06

合わせ

0.06

 lining

0.06

ози

0.06

/fr

0.06

Activations Density 0.013%

Family relations

The neuron fires on kinship and family-relation terms (e.g. father, mother, brother, sister, grand-, nephew, etc.).

No Comments

No Known Activations

Family relations

The neuron fires on kinship and family-relation terms (e.g. father, mother, brother, sister, grand-, nephew, etc.).

No Comments

No Known Activations