INDEX

Explanations

numerical values that denote iterations or state changes in a process or algorithm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.15

iasi

-0.15

...

-0.14

 healing

-0.14

YD

-0.14

 onBind

-0.14

enever

-0.14

Sent

-0.13

 salute

-0.13

www

-0.13

POSITIVE LOGITS

ASM

0.14

à¸°

0.14

tÃ©

0.14

uckets

0.13

ÑĢÐ¾Ñİ

0.13

terdam

0.13

ogra

0.13

rtle

0.13

åĽº

0.13

agma

0.13

Activations Density 0.071%

numerical values that denote iterations or state changes in a process or algorithm

No Comments

No Known Activations