INDEX

Explanations

study

np_max-act · gemini-2.0-flash

The neuron is keyed to phrases naming study designs (e.g. “case–control study,” “prospective randomized study”).

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

manual

-0.07

-floating

-0.07

field

-0.07

ffen

-0.07

 Lebens

-0.06

lıklar

-0.06

BR

-0.06

 مؤ

-0.06

렌

-0.06

POSITIVE LOGITS

(nn

0.06

 informace

0.06

 `,↵

0.06

.writerow

0.06

 uncomment

0.06

 hız

0.06

 thăm

0.06

 mockMvc

0.06

usz

0.06

 swiper

0.06

Activations Density 0.021%

study

The neuron is keyed to phrases naming study designs (e.g. “case–control study,” “prospective randomized study”).

No Comments

No Known Activations