INDEX

Explanations

career progression and work experience details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

ampo

-0.18

ãģ£ãģ

-0.16

Ã¡bado

-0.15

ingles

-0.15

allon

-0.15

 Propel

-0.15

 Shock

-0.15

ulis

-0.14

 ÑĥÐ¶

-0.14

omit

-0.14

POSITIVE LOGITS

rompt

0.16

ãĥ¥ãĥ¼

0.15

0.14

ipar

0.14

RTC

0.14

 manoe

0.13

skins

0.13

oug

0.13

DbType

0.13

Activations Density 0.059%

career progression and work experience details

No Comments

No Known Activations