INDEX

Explanations

terms related to cyber security threats and breaches

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

-fontawesome

-0.17

VRT

-0.14

ervas

-0.14

asurable

-0.14

ALAR

-0.14

luv

-0.13

ersen

-0.13

eyin

-0.13

Ã¶y

-0.13

.FieldName

-0.13

POSITIVE LOGITS

 hacks

0.29

 hacking

0.28

 attacks

0.27

 viruses

0.26

Tro

0.26

 spear

0.26

 worms

0.25

 hackers

0.25

 exploits

0.25

 phishing

0.24

Activations Density 0.104%

terms related to cyber security threats and breaches

No Comments

No Known Activations