INDEX

Explanations

Best

np_max-act · gemini-2.0-flash

The neuron fires on phrasing that describes generating multiple candidate solutions and selecting or ranking the top one.

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

'+

-0.06

 Richmond

-0.06

 domest

-0.06

 NODE

-0.06

.grp

-0.06

 anguish

-0.06

.sup

-0.06

coords

-0.06

ein

-0.05

"sync

-0.05

POSITIVE LOGITS

 xét

0.07

 Enlightenment

0.07

 cravings

0.06

adir

0.06

IRS

0.06

佛

0.06

 асп

0.06

ieme

0.06

/K

0.06

先

0.06

Activations Density 0.027%

Best

The neuron fires on phrasing that describes generating multiple candidate solutions and selecting or ranking the top one.

No Comments

No Known Activations