INDEX

Explanations

phrases related to the quality and characteristics of products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ãĤĪãģĨãģª

-0.20

ãģĬ

-0.17

ãĤĪãģĨãģ«

-0.15

ä¸ĢåĪĩ

-0.15

unas

-0.15

äººæ°Ĺ

-0.15

å¤§

-0.15

ä¸Ģçº§

-0.14

ØªÙī

-0.14

orem

-0.14

POSITIVE LOGITS

 sorts

0.31

course

0.26

0.25

/from

0.22

vido

0.21

 course

0.20

-course

0.19

/by

0.18

/to

0.15

ftime

0.15

Activations Density 1.671%

phrases related to the quality and characteristics of products or services

No Comments

No Known Activations