INDEX

Explanations

references to historical texts and their edits or manuscripts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

arella

-0.15

 Writes

-0.14

 escrit

-0.14

etag

-0.14

Descriptions

-0.14

.writ

-0.14

ftime

-0.13

Ã¡lt

-0.13

Extension

-0.13

reh

-0.13

POSITIVE LOGITS

 edition

0.32

 editions

0.31

edition

0.29

 Edition

0.28

Edition

0.24

æł¡

0.22

fac

0.21

 æł¡

0.21

 apparatus

0.21

 phil

0.20

Activations Density 0.137%

references to historical texts and their edits or manuscripts

No Comments

No Known Activations