INDEX

Explanations

references to ISO standards and certifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

unto

-0.15

Ã³z

-0.15

azes

-0.15

Î¿Ïħ

-0.15

rik

-0.15

uta

-0.15

unta

-0.14

ut

-0.14

Om

-0.14

Î¹Î½Î®

-0.14

POSITIVE LOGITS

abelle

0.19

iec

0.18

ctal

0.18

0.17

abella

0.16

à¸§à¸£à¸£

0.16

0.15

 Downs

0.15

DIS

0.15

Activations Density 0.015%

references to ISO standards and certifications

No Comments

No Known Activations