INDEX

Explanations

groups

np_max-act · gemini-2.0-flash

The neuron activates on phrases describing animals’ social behavior, especially mentions of living in groups, herds, or communal social structures.

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

 Geoff

-0.07

.curr

-0.06

Porn

-0.06

unny

-0.06

clients

-0.06

oured

-0.06

 treasures

-0.06

ederation

-0.06

vehicle

-0.06

izontal

-0.06

POSITIVE LOGITS

ez

0.08

¡

0.07

 brighter

0.06

 tweaking

0.06

 olması

0.06

 initially

0.06

 Formation

0.06

 formation

0.06

(QL

0.06

 implements

0.06

Activations Density 0.013%

groups

The neuron activates on phrases describing animals’ social behavior, especially mentions of living in groups, herds, or communal social structures.

No Comments

No Known Activations