INDEX

Explanations

ua

np_max-act · gemini-2.0-flash

This neuron fires on the names of other (proper-noun) articles or entries—e.g. link titles in “See also” or similar lists.

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

generation

-0.07

Rates

-0.06

	product

-0.06

_hour

-0.06

(tool

-0.06

 baskets

-0.06

owers

-0.06

StartDate

-0.06

.generate

-0.06

 прод

-0.06

POSITIVE LOGITS

Xã

0.07

 هو

0.07

_color

0.06

 هي

0.06

 %%↵

0.06

 viên

0.06

_Bool

0.06

.V

0.06

”).

0.06

>):

0.06

Activations Density 0.025%

ua

This neuron fires on the names of other (proper-noun) articles or entries—e.g. link titles in “See also” or similar lists.

No Comments

No Known Activations