INDEX

Explanations

concepts 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 @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

iesen

-0.16

enstein

-0.16

ihan

-0.16

referrer

-0.15

igor

-0.14

Ð°Ð½ÑĤÐ¸

-0.14

rof

-0.14

Transient

-0.13

POSITIVE LOGITS

 safety

0.65

 Safety

0.54

Safety

0.52

 safe

0.47

 safer

0.45

å®īåħ¨

0.45

afety

0.44

 protection

0.42

safe

0.41

saf

0.41

Activations Density 0.164%

concepts related to safety and security

No Comments

No Known Activations