INDEX

Explanations

metrics related to participation and engagement in various activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

roscope

-0.17

raya

-0.15

ORMAL

-0.15

hausen

-0.14

aura

-0.14

duit

-0.14

prar

-0.14

 Ning

-0.14

elik

-0.13

ollo

-0.13

POSITIVE LOGITS

 levels

0.34

 figures

0.33

 numbers

0.33

 rates

0.29

 rate

0.27

numbers

0.27

levels

0.26

 Levels

0.26

figures

0.26

 Figures

0.25

Activations Density 0.193%

metrics related to participation and engagement in various activities or events

No Comments

No Known Activations