INDEX

Explanations

financial metrics and performance indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ç«ĭãģ¡

-0.15

mart

-0.15

 eldre

-0.14

ãĤĵãģ©

-0.14

ropp

-0.14

iel

-0.14

irc

-0.13

 kvinne

-0.13

ereum

-0.13

ongs

-0.13

POSITIVE LOGITS

-basic

0.20

GA

0.18

basic

0.17

$(

0.17

 basic

0.17

 Basic

0.17

attrib

0.17

Dil

0.17

Basic

0.16

/basic

0.16

Activations Density 0.210%

financial metrics and performance indicators

No Comments

No Known Activations