INDEX

Explanations

cooking techniques and tips

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ipl

-0.15

 Ð¾ÑĩÐ¸

-0.15

DUCT

-0.14

isman

-0.14

xic

-0.14

åįĴ

-0.14

 groom

-0.14

 cleans

-0.13

 filt

-0.13

dj

-0.13

POSITIVE LOGITS

 Uniform

0.20

Uniform

0.19

uniform

0.18

èĴ

0.18

 Brow

0.17

 uniforms

0.17

 uniform

0.16

 Ø§ÙĦØ·Ø¨

0.15

 caramel

0.15

 contacto

0.15

Activations Density 0.094%

cooking techniques and tips

No Comments

No Known Activations