INDEX

Explanations

terms and definitions that relate to the concept of terminology or designation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

à¤¾à¤ĸ

-0.15

 folded

-0.15

fred

-0.15

isman

-0.15

lab

-0.14

ogue

-0.14

bo

-0.13

ursors

-0.13

ahlen

-0.13

ifers

-0.13

POSITIVE LOGITS

itecture

0.17

.gameserver

0.16

APTER

0.16

ology

0.15

 Darling

0.15

ãĤ¡

0.14

kening

0.14

viso

0.14

Activations Density 0.049%

terms and definitions that relate to the concept of terminology or designation

No Comments

No Known Activations