INDEX

Explanations

technical terms and expressions related to events and installations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

rozen

-0.17

æĭĽ

-0.15

 weiber

-0.14

Ð¾Ð·ÐµÐ¼

-0.14

uars

-0.14

DDR

-0.14

çĽĺ

-0.14

irtschaft

-0.14

brig

-0.14

Slow

-0.14

POSITIVE LOGITS

 Date

0.28

Date

0.25

-date

0.24

 date

0.23

date

0.22

/date

0.21

odate

0.20

Ben

0.20

Pak

0.20

 setDate

0.20

Activations Density 0.012%

technical terms and expressions related to events and installations

No Comments

No Known Activations