INDEX

Explanations

terms related to cybercrime and security breaches

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

ipay

-0.16

 odpad

-0.15

otos

-0.15

¶Į

-0.15

Asi

-0.14

ãĥªãĤ«

-0.14

ighting

-0.14

idon

-0.14

itre

-0.13

agon

-0.13

POSITIVE LOGITS

 compromise

0.32

 comprom

0.29

 compromises

0.27

 compromising

0.26

 gaining

0.26

 gained

0.25

 gain

0.25

 compromised

0.24

mas

0.24

çª

0.24

Activations Density 0.146%

terms related to cybercrime and security breaches

No Comments

No Known Activations