INDEX

Explanations

significant references to published works and their attributes

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

 Banner

-0.15

acha

-0.14

Banner

-0.14

uture

-0.14

 Courtesy

-0.13

 Fres

-0.13

 Curtain

-0.13

 handwritten

-0.13

Clip

-0.13

_IMPL

-0.13

POSITIVE LOGITS

 book

0.30

 edition

0.22

 volume

0.21

book

0.21

-book

0.20

 editions

0.19

 bound

0.18

obook

0.18

folios

0.18

 ÐºÐ½Ð¸

0.17

Activations Density 0.137%

significant references to published works and their attributes

No Comments

No Known Activations