INDEX

Explanations

denial-of-service (DoS) attacks

np_max-act · gemini-2.0-flash

The neuron activates on descriptions of distributed denial‐of‐service attacks—phrases depicting an attacker using multiple systems to flood or overload a target with a large volume of requests.

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

 David

-0.07

 Lord

-0.07

 Arrest

-0.07

(level

-0.06

modation

-0.06

idential

-0.06

Damn

-0.06

EEDED

-0.06

 Hash

-0.06

 Iran

-0.06

POSITIVE LOGITS

 ),↵↵

0.06

 Vulner

0.06

 kork

0.06

药

0.06

obao

0.06

)*(

0.06

]?.

0.06

 IconButton

0.06

Todo

0.06

$string

0.06

Activations Density 0.005%

denial-of-service (DoS) attacks

The neuron activates on descriptions of distributed denial‐of‐service attacks—phrases depicting an attacker using multiple systems to flood or overload a target with a large volume of requests.

No Comments

No Known Activations