INDEX

Explanations

topics related to safety and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 safely

-0.24

 safer

-0.22

 safest

-0.20

safe

-0.19

.Safe

-0.19

Safe

-0.18

 Safe

-0.17

_SAFE

-0.17

 Safety

-0.17

 ìķĪìłĦ

-0.16

POSITIVE LOGITS

 security

0.24

security

0.20

-security

0.20

 sound

0.20

Security

0.19

 Sound

0.19

 Security

0.19

Sound

0.17

erville

0.17

 SOUND

0.16

Activations Density 0.045%

topics related to safety and security

No Comments

No Known Activations