INDEX

Explanations

language and discussions related to planning and scheduling events or appointments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ÑĪÐ»Ð¾

-0.14

ä¸Ķ

-0.14

rios

-0.13

olon

-0.13

ãģ¾ãģŁ

-0.13

obil

-0.13

isay

-0.13

Î³Ïĩ

-0.13

ierge

-0.13

à¹Ģà¸¥à¸¢

-0.13

POSITIVE LOGITS

so

0.86

 afin

0.46

so

0.45

 sÃ¥

0.41

 ÑĩÑĤÐ¾Ð±Ñĭ

0.39

å¦ĤæŃ¤

0.39

 Ïİ

0.37

ãģ®ãģ§

0.36

æīĢä»¥

0.36

 ÑĤÐ°Ðº

0.34

Activations Density 0.815%

language and discussions related to planning and scheduling events or appointments

No Comments

No Known Activations