INDEX

Explanations

shootings and massacres

np_max-act · gemini-2.0-flash

This neuron fires on words referring to large‐scale or mass violence (e.g. terrorism, mass shootings, massacres).

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

 survival

-0.08

/em

-0.07

-0.06

tmp

-0.06

�

-0.06

/book

-0.06

 multiplier

-0.06

 pause

-0.06

/download

-0.06

روج

-0.06

POSITIVE LOGITS

�부

0.08

Las

0.07

�

0.07

ourced

0.07

,date

0.07

(Activity

0.06

 Shower

0.06

 мис

0.06

 postcode

0.06

olithic

0.06

Activations Density 0.017%

shootings and massacres

This neuron fires on words referring to large‐scale or mass violence (e.g. terrorism, mass shootings, massacres).

No Comments

No Known Activations

shootings and massacres

This neuron fires on words referring to large‐scale or mass violence (e.g. terrorism, mass shootings, massacres).

No Comments

No Known Activations