INDEX

Explanations

int

np_max-act · gemini-2.0-flash

The neuron never fires (all activation values are zero), i.e. it does not detect any pattern in the input.

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

Pop

-0.07

Over

-0.07

avirus

-0.07

LoggedIn

-0.06

CAT

-0.06

женер

-0.06

blur

-0.06

 الوف

-0.06

елик

-0.06

อท

-0.06

POSITIVE LOGITS

던

0.07

ustralian

0.06

 collaps

0.06

 fact

0.06

 sighting

0.06

 ninja

0.06

 shrine

0.06

.setValue

0.06

jen

0.06

 INTERN

0.06

Activations Density 0.005%

int

The neuron never fires (all activation values are zero), i.e. it does not detect any pattern in the input.

No Comments

No Known Activations

int

The neuron never fires (all activation values are zero), i.e. it does not detect any pattern in the input.

No Comments

No Known Activations