INDEX

Explanations

phrases related to safety precautions and concerns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

æŁ³

-0.17

vailability

-0.16

ÑĦÐ¸ÐºÐ°

-0.14

olec

-0.14

entifier

-0.14

 Äĳá»ķ

-0.14

emap

-0.14

atan

-0.13

ollapse

-0.13

CCR

-0.13

POSITIVE LOGITS

 safety

0.35

 Safety

0.27

 security

0.26

å®īåħ¨

0.26

Safety

0.26

afety

0.25

 privacy

0.23

 protection

0.21

 ethical

0.20

 Ð±ÐµÐ·Ð¾Ð¿Ð°ÑģÐ½Ð¾ÑģÑĤÐ¸

0.19

Activations Density 0.461%

phrases related to safety precautions and concerns

No Comments

No Known Activations