INDEX

Explanations

comma

np_max-act · gemini-2.0-flash

The neuron is selectively activating on numeric tokens (particularly decimal-formatted numbers) in the text.

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

toupper

-0.07

etas

-0.07

칭

-0.07

禮

-0.06

_foot

-0.06

 Leafs

-0.06

esta

-0.06

-esteem

-0.06

QUEUE

-0.06

 archived

-0.06

POSITIVE LOGITS

戰

0.07

送料無料

0.07

Obs

0.07

lj

0.06

 přím

0.06

 riêng

0.06

세요

0.06

 skon

0.06

 pomoc

0.06

.utility

0.06

Activations Density 0.003%

comma

The neuron is selectively activating on numeric tokens (particularly decimal-formatted numbers) in the text.

No Comments

No Known Activations

comma

The neuron is selectively activating on numeric tokens (particularly decimal-formatted numbers) in the text.

No Comments

No Known Activations