INDEX

Explanations

car sales

np_max-act · gemini-2.0-flash

The neuron flags tokens that specify a vehicle’s details (e.g. year, make, model, and the word “car”).

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

Bytes

-0.07

URT

-0.07

irth

-0.06

roleum

-0.06

association

-0.06

ेव

-0.06

-service

-0.06

zaz

-0.06

 Workflow

-0.06

 Antarctica

-0.06

POSITIVE LOGITS

_DEFINED

0.08

 слишком

0.06

 allergic

0.06

}?

0.06

(nullptr

0.06

 mimetype

0.06

 yıllık

0.06

 cultiv

0.06

(elem

0.06

.quality

0.06

Activations Density 0.028%

car sales

The neuron flags tokens that specify a vehicle’s details (e.g. year, make, model, and the word “car”).

No Comments

No Known Activations

car sales

The neuron flags tokens that specify a vehicle’s details (e.g. year, make, model, and the word “car”).

No Comments

No Known Activations