INDEX

Explanations

references to cybersecurity threats and issues related to data protection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÌĨ

-0.17

posites

-0.14

enin

-0.14

å¾³

-0.14

anas

-0.14

angep

-0.14

pov

-0.13

annels

-0.13

getBlock

-0.13

XR

-0.13

POSITIVE LOGITS

 sensitive

0.65

-sensitive

0.52

Sensitive

0.50

ensitive

0.47

 sensitivity

0.42

æķı

0.38

_sensitive

0.37

 confidential

0.35

 sensit

0.35

 critical

0.30

Activations Density 0.218%

references to cybersecurity threats and issues related to data protection

No Comments

No Known Activations