INDEX

Explanations

@

np_max-act · gemini-2.0-flash

This neuron activates on tokens that are parts of email addresses (e.g. user@domain fragments) in message headers.

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

,\

-0.06

lost

-0.06

 slik

-0.06

.eng

-0.06

Jap

-0.06

-wave

-0.06

 Capacity

-0.06

ACITY

-0.06

kas

-0.06

POSITIVE LOGITS

abis

0.07

(cl

0.06

")!=

0.06

getContent

0.06

_aa

0.06

photo

0.06

NFL

0.06

 candy

0.06

وقع

0.06

 Marion

0.06

Activations Density 0.003%

@

This neuron activates on tokens that are parts of email addresses (e.g. user@domain fragments) in message headers.

No Comments

No Known Activations

@

This neuron activates on tokens that are parts of email addresses (e.g. user@domain fragments) in message headers.

No Comments

No Known Activations