INDEX

Explanations

God

np_max-act · gemini-2.0-flash

This neuron specifically fires on the token “God” (and its possessive “God’s”).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

references to financial issues and the impacts of budgetary decisions.

oai_token-act-pair · gpt-4o-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

 ince

-0.08

 March

-0.07

ریز

-0.07

 Vance

-0.07

 snippet

-0.07

 precarious

-0.07

March

-0.07

 Irving

-0.07

-line

-0.07

 Ranch

-0.07

POSITIVE LOGITS

God

0.15

God

0.13

god

0.12

GOD

0.12

天

0.09

 gods

0.08

 Gods

0.08

ゴ

0.08

天

0.07

 ГО

0.07

Activations Density 0.014%

God

This neuron specifically fires on the token “God” (and its possessive “God’s”).

references to financial issues and the impacts of budgetary decisions.

No Comments

No Known Activations