INDEX

Explanations

references to tattoos and tattoo culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

utters

-0.17

bundle

-0.15

åĩºçīĪç¤¾

-0.14

 useForm

-0.14

ccd

-0.14

//{{

-0.14

è¦ĸ

-0.14

ikki

-0.14

ÑĨÐ¸ÑıÑħ

-0.13

 Bend

-0.13

POSITIVE LOGITS

 tattoo

0.46

ink

0.44

 tattoos

0.41

 Tattoo

0.39

Ink

0.38

 Tatto

0.35

 tatto

0.34

tat

0.30

 tato

0.27

ink

0.27

Activations Density 0.042%

references to tattoos and tattoo culture

No Comments

No Known Activations