INDEX

Explanations

terms related to make-up and hair industry practices

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

å¾½

-0.16

rica

-0.15

orgetown

-0.14

ãĥ©ãĥĥãĤ¯

-0.14

erable

-0.14

.Serve

-0.14

ĳ

-0.14

icter

-0.14

postalcode

-0.14

nech

-0.14

POSITIVE LOGITS

 hair

0.38

 hairst

0.35

 salon

0.34

 Hair

0.34

hair

0.34

Hair

0.32

 Salon

0.32

 haircut

0.28

 stylist

0.26

 styling

0.26

Activations Density 0.062%

terms related to make-up and hair industry practices

No Comments

No Known Activations