INDEX

Explanations

mentions of "brand new" products or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

herits

-0.18

HEME

-0.16

ãĥ¬ãĤ¤

-0.15

uteur

-0.15

awei

-0.15

esti

-0.14

 ëĭ¤ìļ´ë°Ľê¸°

-0.14

wart

-0.13

 ë°°

-0.13

ags

-0.13

POSITIVE LOGITS

TON

0.18

utex

0.17

uluk

0.17

rna

0.15

isz

0.15

ton

0.15

ç§Ģ

0.15

assist

0.15

0.14

erta

0.14

Activations Density 0.012%

mentions of "brand new" products or items

No Comments

No Known Activations