INDEX

Explanations

diagnosed

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect mentions of “website” or “websites.”

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

 open

-0.07

 fashion

-0.06

(Person

-0.06

nerRadius

-0.06

_CONTROLLER

-0.06

 Liqu

-0.06

 phong

-0.06

 inspected

-0.06

 Petroleum

-0.06

.Payment

-0.06

POSITIVE LOGITS

 المج

0.07

	response

0.06

".

0.06

 insightful

0.06

shouldReceive

0.06

 Traff

0.06

XM

0.06

career

0.06

_EVT

0.06

име

0.06

Activations Density 0.000%

diagnosed

The main thing this neuron does is detect mentions of “website” or “websites.”

No Comments

No Known Activations