INDEX

Explanations

.Ret

np_max-act · gemini-2.0-flash

The neuron fires on Java annotation-retention declarations (i.e. the “@Retention” annotation).

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

Chi

-0.07

ух

-0.06

 flaming

-0.06

 очевид

-0.06

“Oh

-0.06

Charlotte

-0.06

投

-0.06

owl

-0.06

 Healing

-0.06

 Carpet

-0.06

POSITIVE LOGITS

.Menu

0.08

.elasticsearch

0.07

.Ret

0.07

OptionsMenu

0.07

.Quad

0.06

	Send

0.06

 Россия

0.06

Hà

0.06

enegro

0.06

coon

0.06

Activations Density 0.000%

.Ret

The neuron fires on Java annotation-retention declarations (i.e. the “@Retention” annotation).

No Comments

No Known Activations

.Ret

The neuron fires on Java annotation-retention declarations (i.e. the “@Retention” annotation).

No Comments

No Known Activations