INDEX

Explanations

,

np_max-act · gemini-2.0-flash

The neuron activates on orchestration and instrumentation lists, i.e. the names of instruments in a work’s scoring.

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

암

-0.07

PH

-0.06

neighbor

-0.06

 yurt

-0.06

 native

-0.06

gia

-0.06

 Wright

-0.06

 다양

-0.06

.contract

-0.06

 olup

-0.06

POSITIVE LOGITS

ней

0.07

spy

0.06

ackers

0.06

akeup

0.06

thin

0.06

 Gambling

0.06

 desire

0.06

 experiencia

0.06

Activations Density 0.006%

,

The neuron activates on orchestration and instrumentation lists, i.e. the names of instruments in a work’s scoring.

No Comments

No Known Activations

,

The neuron activates on orchestration and instrumentation lists, i.e. the names of instruments in a work’s scoring.

No Comments

No Known Activations