INDEX

Explanations

to be

np_max-act · gemini-2.0-flash

The neuron strongly fires on transactional‐status and timing words—that is, tokens like “completed,” “delivered,” “received,” “within,” “after,” “days,” “hours,” etc., marking when work, payment, or shipping milestones occur.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

content related to writing opportunities or job descriptions.

oai_token-act-pair · gpt-4o-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

화

-0.06

付

-0.06

Inactive

-0.06

三三

-0.06

 organizational

-0.06

typ

-0.06

 lazy

-0.06

مس

-0.06

ushman

-0.06

 verk

-0.06

POSITIVE LOGITS

-production

0.07

 الزر

0.07

等

0.06

larını

0.06

bron

0.06

 để

0.06

 gerektiğini

0.06

-themed

0.06

(routes

0.06

errorMessage

0.06

Activations Density 0.021%

to be

The neuron strongly fires on transactional‐status and timing words—that is, tokens like “completed,” “delivered,” “received,” “within,” “after,” “days,” “hours,” etc., marking when work, payment, or shipping milestones occur.

content related to writing opportunities or job descriptions.

No Comments

No Known Activations

to be

The neuron strongly fires on transactional‐status and timing words—that is, tokens like “completed,” “delivered,” “received,” “within,” “after,” “days,” “hours,” etc., marking when work, payment, or shipping milestones occur.

content related to writing opportunities or job descriptions.

No Comments

No Known Activations