INDEX

Explanations

nitrogen

np_max-act · gemini-2.0-flash

This neuron responds to the names of specific gases (e.g. methane, hydrogen, oxygen, nitrogen, carbon dioxide).

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

 chị

-0.07

appen

-0.07

HU

-0.06

INFO

-0.06

 Pasadena

-0.06

cou

-0.06

coni

-0.06

음

-0.06

상품

-0.06

etsk

-0.06

POSITIVE LOGITS

.cb

0.07

 Sitting

0.07

Ib

0.07

 Ου

0.06

(suffix

0.06

idUser

0.06

brit

0.06

Ana

0.06

 nitrogen

0.06

uous

0.06

Activations Density 0.007%

nitrogen

This neuron responds to the names of specific gases (e.g. methane, hydrogen, oxygen, nitrogen, carbon dioxide).

No Comments

No Known Activations