INDEX

Explanations

topics related to cybersecurity threats and adversaries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

eci

-0.14

 Disaster

-0.14

 Jungle

-0.14

ÙĬØ§Øª

-0.14

 traj

-0.14

uai

-0.14

uzzi

-0.13

 amnesty

-0.13

arty

-0.13

Unsafe

-0.13

POSITIVE LOGITS

 hack

0.33

 hacking

0.33

 cyber

0.32

hack

0.28

cy

0.28

 Hack

0.27

 hacks

0.27

 hackers

0.26

 Cyber

0.26

cy

0.25

Activations Density 0.104%

topics related to cybersecurity threats and adversaries

No Comments

No Known Activations