INDEX

Explanations

com

np_max-act · gemini-2.0-flash

The neuron flags mentions of concurrent or accompanying factors, especially the word “concomitant.”

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

 eager

-0.07

 cleanup

-0.07

 unters

-0.07

 бизнес

-0.07

 آب

-0.06

.YesNo

-0.06

 TEST

-0.06

UPS

-0.06

láš

-0.06

 dikke

-0.06

POSITIVE LOGITS

 correlates

0.07

 concurrent

0.06

cca

0.06

/inet

0.06

!")↵

0.06

 Accom

0.06

κολ

0.06

sahuje

0.06

readcrumb

0.06

υκ

0.06

Activations Density 0.004%

com

The neuron flags mentions of concurrent or accompanying factors, especially the word “concomitant.”

No Comments

No Known Activations