INDEX

Explanations

references to authors, books, and literary works

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

olia

-0.17

ì§ĵ

-0.15

ORITY

-0.15

_Style

-0.15

å¾ĭ

-0.14

ovice

-0.14

ìĬ¹

-0.14

Property

-0.14

 Property

-0.14

kan

-0.14

POSITIVE LOGITS

 bookstore

0.32

 Books

0.28

 Book

0.28

 book

0.27

 books

0.27

 independent

0.25

 bibli

0.25

 independents

0.25

Books

0.25

 Independent

0.23

Activations Density 0.065%

references to authors, books, and literary works

No Comments

No Known Activations