INDEX

Explanations

aper

np_max-act · gemini-2.0-flash

The neuron is essentially dead—it never activates on any tokens.

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

 Moody

-0.07

，默认

-0.06

��

-0.06

۲۳

-0.06

kW

-0.06

ITUDE

-0.06

ifica

-0.06

棋

-0.06

plr

-0.06

 Boss

-0.06

POSITIVE LOGITS

 Caught

0.07

.gold

0.06

オ

0.06

-final

0.06

/store

0.06

 clicks

0.06

	store

0.06

(pg

0.06

ट

0.06

ัดการ

0.06

Activations Density 0.000%

aper

The neuron is essentially dead—it never activates on any tokens.

No Comments

No Known Activations

aper

The neuron is essentially dead—it never activates on any tokens.

No Comments

No Known Activations