INDEX

Explanations

The neuron primarily activates on numeric tokens (digits and numeric measurements, often paired with units).

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

_successful

-0.07

_boundary

-0.07

 elder

-0.07

 secre

-0.06

์ค

-0.06

Pe

-0.06

getJSON

-0.06

utom

-0.06

 eleştir

-0.06

	connection

-0.06

POSITIVE LOGITS

fid

0.07

 mime

0.06

 너무

0.06

£

0.06

("\(

0.06

sad

0.06

(_

0.06

$_

0.06

 psik

0.06

 vztah

0.06

Activations Density 0.071%

The neuron primarily activates on numeric tokens (digits and numeric measurements, often paired with units).

No Comments

No Known Activations

The neuron primarily activates on numeric tokens (digits and numeric measurements, often paired with units).

No Comments

No Known Activations