INDEX

Explanations

references to health-related issues and diseases

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

imus

-0.16

opot

-0.16

Ses

-0.15

Verdana

-0.15

DN

-0.14

.Networking

-0.14

imens

-0.14

)./

-0.14

Ãªu

-0.13

peon

-0.13

POSITIVE LOGITS

 kuru

0.31

pr

0.30

 scrap

0.28

 Scrap

0.25

Cre

0.23

 Variant

0.23

 brain

0.22

 brains

0.22

 transmission

0.21

brains

0.21

Activations Density 0.008%

references to health-related issues and diseases

No Comments

No Known Activations