INDEX

Explanations

of the

np_max-act · gemini-2.0-flash

The neuron detects mentions of institutional affiliations (e.g. university or department names).

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

grd

-0.07

vk

-0.06

 برابر

-0.06

Scheme

-0.06

 Раз

-0.06

elapsed

-0.06

 ذات

-0.06

 edition

-0.06

Pan

-0.06

Ze

-0.06

POSITIVE LOGITS

üns

0.07

(term

0.06

-react

0.06

 lobbying

0.06

 popularity

0.06

 polož

0.06

 quantitative

0.06

 Jewelry

0.06

 nepří

0.06

 العربي

0.06

Activations Density 0.019%

of the

The neuron detects mentions of institutional affiliations (e.g. university or department names).

No Comments

No Known Activations