INDEX

Explanations

d

np_max-act · gemini-2.0-flash

This neuron is effectively inactive—it doesn’t respond to 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

 Idle

-0.07

_ING

-0.06

apus

-0.06

卓

-0.06

getColumn

-0.06

orgh

-0.06

 STAR

-0.06

 reinc

-0.06

Stick

-0.06

 Ramadan

-0.06

POSITIVE LOGITS

 tutorial

0.07

=_("

0.07

/umd

0.06

!</

0.06

(moment

0.06

 motion

0.06

thickness

0.06

idi

0.06

Activations Density 0.004%

d

This neuron is effectively inactive—it doesn’t respond to any tokens.

No Comments

No Known Activations