INDEX

Explanations

in

np_max-act · gemini-2.0-flash

The neuron never fires—it does not respond to any tokens and so has no identifiable pattern.

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

Japgolly

-0.06

 english

-0.06

 Harvard

-0.06

 Пол

-0.06

ičky

-0.06

 slide

-0.06

 fucking

-0.06

_EXPI

-0.06

 sorted

-0.06

urai

-0.06

POSITIVE LOGITS

.views

0.06

Oi

0.06

 *)↵↵

0.06

สนาม

0.06

 граф

0.06

ctxt

0.06

 چین

0.06

.getRight

0.06

 Nationwide

0.06

Activations Density 0.000%

in

The neuron never fires—it does not respond to any tokens and so has no identifiable pattern.

No Comments

No Known Activations