INDEX

Explanations

URLs or identifiers related to web security and vulnerabilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 Minority

-0.15

 tslib

-0.15

autÃ©

-0.15

quan

-0.15

att

-0.15

-0.14

sid

-0.14

ç§ĳ

-0.14

-0.13

POSITIVE LOGITS

urer

0.17

onga

0.15

itin

0.15

íĿ¬

0.15

kest

0.14

ÏĥÎ¼Î±

0.14

_SECURE

0.14

 ÙħØ¨Ø§Ø´

0.14

mdi

0.13

 Inflate

0.13

Activations Density 0.048%

URLs or identifiers related to web security and vulnerabilities

No Comments

No Known Activations