INDEX

Explanations

details related to image quality and resolution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

chg

-0.17

erer

-0.16

anz

-0.15

avenport

-0.14

ylie

-0.14

ength

-0.14

á»£

-0.14

redi

-0.13

 deport

-0.13

uniq

-0.13

POSITIVE LOGITS

 resolution

0.32

 detail

0.30

Resolution

0.27

 Resolution

0.27

/detail

0.26

detail

0.26

-resolution

0.25

 resolutions

0.25

 artifact

0.25

 Detail

0.25

Activations Density 0.078%

details related to image quality and resolution

No Comments

No Known Activations