INDEX

Explanations

references to social media usage and personal profiles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Peters

-0.15

placements

-0.15

cola

-0.15

\xff

-0.14

 Whatsapp

-0.14

 ç¿

-0.14

Ã£n

-0.14

 legit

-0.13

/sdk

-0.13

 chew

-0.13

POSITIVE LOGITS

 profile

0.72

 Profile

0.61

profile

0.60

Profile

0.55

-profile

0.54

 profiles

0.53

_profile

0.53

 PROFILE

0.53

.profile

0.50

 profil

0.48

Activations Density 0.094%

references to social media usage and personal profiles

No Comments

No Known Activations

references to social media usage and personal profiles

No Comments

No Known Activations