INDEX

Explanations

keywords related to cybersecurity threats and exploits

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Cy

-0.16

zza

-0.15

dep

-0.15

dag

-0.14

 Cyber

-0.14

_CPU

-0.14

 druÅ¾

-0.14

 Psychiat

-0.14

Rum

-0.14

emacs

-0.14

POSITIVE LOGITS

 infected

0.21

Tor

0.21

 compromised

0.20

 hone

0.19

 victims

0.19

Exposed

0.18

 victim

0.18

 legitimate

0.18

bot

0.17

 machines

0.17

Activations Density 0.119%

keywords related to cybersecurity threats and exploits

No Comments

No Known Activations