INDEX

Explanations

expressions of love and affection

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

eson

-0.15

.scalablytyped

-0.15

apg

-0.15

angl

-0.14

ymes

-0.14

ÑģÑĥÑĤ

-0.13

posium

-0.13

amate

-0.13

pected

-0.13

POSITIVE LOGITS

 adore

0.28

 absolutely

0.27

lo

0.26

ad

0.25

 absolut

0.24

 fell

0.23

 absolute

0.23

swo

0.22

LO

0.22

 absol

0.22

Activations Density 0.153%

expressions of love and affection

No Comments

No Known Activations