INDEX

Explanations

explosions and disasters

np_max-act · gemini-2.0-flash

The neuron activates on words that mark the sequential ordering of events—especially ordinals and event‐sequence terms (e.g. “first,” “second,” “third,” “blast,” “exploded,” etc.).

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

 Tài

-0.07

cích

-0.06

Lord

-0.06

 vista

-0.06

 gearbox

-0.06

isi

-0.06

.PERMISSION

-0.06

定

-0.06

Flags

-0.06

ol

-0.06

POSITIVE LOGITS

(version

0.07

#![

0.07

 QLatin

0.06

ứt

0.06

.isLoading

0.06

 відбувається

0.06

-border

0.06

.confirm

0.06

ezpeč

0.06

aggio

0.06

Activations Density 0.014%

explosions and disasters

The neuron activates on words that mark the sequential ordering of events—especially ordinals and event‐sequence terms (e.g. “first,” “second,” “third,” “blast,” “exploded,” etc.).

No Comments

No Known Activations

explosions and disasters

The neuron activates on words that mark the sequential ordering of events—especially ordinals and event‐sequence terms (e.g. “first,” “second,” “third,” “blast,” “exploded,” etc.).

No Comments

No Known Activations