INDEX

Explanations

words and phrases associated with personalized gifts and experiences

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

èĳĹ

-0.15

atars

-0.14

azzo

-0.14

egasus

-0.14

aryawan

-0.14

 fucked

-0.14

ØªÙī

-0.13

:Number

-0.13

ìĬ¹

-0.13

 Drugs

-0.13

POSITIVE LOGITS

die

0.33

 discern

0.31

 avid

0.30

 discrim

0.29

 serious

0.28

 aficion

0.27

die

0.27

con

0.27

 seasoned

0.26

 devoted

0.25

Activations Density 0.211%

words and phrases associated with personalized gifts and experiences

No Comments

No Known Activations