INDEX

Explanations

elements related to visual editing and photography

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

 Pennsylvania

-0.14

 Penn

-0.13

ownt

-0.13

arp

-0.13

oman

-0.13

phabet

-0.13

Penn

-0.13

.synthetic

-0.13

glas

-0.13

perial

-0.12

POSITIVE LOGITS

 highlights

0.28

 exposure

0.27

 Exposure

0.26

 Highlights

0.26

 Highlight

0.25

 highlight

0.25

 Recovery

0.24

 recovery

0.24

 histogram

0.24

 saturation

0.23

Activations Density 0.012%

elements related to visual editing and photography

No Comments

No Known Activations