INDEX

Explanations

words and phrases related to safety issues and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

soever

-0.15

istrovstvÃŃ

-0.15

Ã©is

-0.15

ETERS

-0.15

lie

-0.14

idia

-0.14

Ã¼hl

-0.14

 Peters

-0.14

ly

-0.14

æľ«

-0.14

POSITIVE LOGITS

/security

0.24

-minded

0.17

/fire

0.17

ably

0.17

ETY

0.17

 minded

0.16

-net

0.16

 margins

0.15

.Cryptography

0.15

belt

0.15

Activations Density 0.028%

words and phrases related to safety issues and regulations

No Comments

No Known Activations