INDEX

Explanations

for

np_max-act · gemini-2.0-flash

This neuron specifically detects the word “for” in the licensing boilerplate (e.g. “See LICENSE.txt for …”).

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

Dark

-0.07

medium

-0.07

Strange

-0.06

igmatic

-0.06

tac

-0.06

/************************************************

-0.06

 sensitive

-0.06

lix

-0.06

έ

-0.06

 zijn

-0.06

POSITIVE LOGITS

POCH

0.07

[length

0.07

deer

0.07

 Vacc

0.07

 Vander

0.06

Andrew

0.06

 руковод

0.06

 Toastr

0.06

知

0.06

्ञ

0.06

Activations Density 0.002%

for

This neuron specifically detects the word “for” in the licensing boilerplate (e.g. “See LICENSE.txt for …”).

No Comments

No Known Activations