INDEX

Explanations

elements related to photo editing and enhancement processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

anship

-0.14

Spell

-0.14

arp

-0.14

ahn

-0.14

ownt

-0.14

_decorator

-0.13

 Spell

-0.13

 Hunger

-0.13

 ØªØµÙħÙĬÙħ

-0.13

jezd

-0.13

POSITIVE LOGITS

 highlight

0.25

 highlights

0.25

 Highlights

0.25

 saturation

0.23

 Recover

0.23

 exposure

0.22

 Highlight

0.22

 Recovery

0.22

 recovery

0.22

recover

0.22

Activations Density 0.008%

elements related to photo editing and enhancement processes

No Comments

No Known Activations