INDEX

Explanations

references to official awards or medals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

.attach

-0.19

allee

-0.16

attach

-0.15

 YELLOW

-0.15

æķĻ

-0.15

éĻ£

-0.14

æĹıèĩªæ²»

-0.14

ä¾

-0.14

POSITIVE LOGITS

 legend

0.26

 legends

0.24

 laure

0.21

legend

0.21

wre

0.19

 date

0.19

ins

0.19

 bust

0.19

ob

0.18

 field

0.18

Activations Density 0.030%

references to official awards or medals

No Comments

No Known Activations