INDEX

Explanations

phrases related to summaries, discussions, and lists of information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Manuals

-0.15

çĻ

-0.15

ä¿ĥ

-0.15

acock

-0.14

 ters

-0.14

ipzig

-0.14

åĩĮ

-0.14

shine

-0.14

land

-0.14

POSITIVE LOGITS

 overview

0.28

 breakdown

0.27

 brief

0.26

 guide

0.24

 summary

0.24

 list

0.23

 primer

0.23

 look

0.22

overview

0.21

 rundown

0.21

Activations Density 0.159%

phrases related to summaries, discussions, and lists of information

No Comments

No Known Activations