INDEX

Explanations

phrases and terms associated with quality and superiority in products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ums

-0.15

zin

-0.14

usan

-0.14

@student

-0.13

itan

-0.13

aver

-0.13

regor

-0.13

zem

-0.12

issen

-0.12

insky

-0.12

POSITIVE LOGITS

 quality

0.82

quality

0.71

-quality

0.66

 Quality

0.63

Quality

0.60

 QUAL

0.59

_quality

0.57

.quality

0.54

 calidad

0.54

è´¨éĩı

0.54

Activations Density 0.197%

phrases and terms associated with quality and superiority in products or services

No Comments

No Known Activations