INDEX

Explanations

phrases indicating usability and features of a photo enhancement application

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

aset

-0.16

ombat

-0.16

izo

-0.15

 Carousel

-0.14

enn

-0.14

ÑĸÐ¶

-0.14

elix

-0.14

Ø¯Ø§Ø¯

-0.14

Fro

-0.13

abyrin

-0.13

POSITIVE LOGITS

pong

0.18

ê¶Į

0.18

 maxim

0.16

çľł

0.15

Undo

0.15

allee

0.14

_EXTERN

0.14

 obed

0.14

Ĳ

0.14

onus

0.14

Activations Density 0.005%

phrases indicating usability and features of a photo enhancement application

No Comments

No Known Activations