INDEX

Explanations

numerical references, particularly related to dates and statistics involving COVID-19

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

amina

-0.17

ocard

-0.15

Ã¡tis

-0.15

artner

-0.15

aire

-0.15

iera

-0.14

$LANG

-0.14

aine

-0.14

errer

-0.14

POSITIVE LOGITS

0.41

âĢ²

0.31

âĢ³

0.29

ï¸ı

0.27

ska

0.22

sus

0.20

sheets

0.19

sak

0.19

sand

0.18

eters

0.17

Activations Density 0.188%

numerical references, particularly related to dates and statistics involving COVID-19

No Comments

No Known Activations