INDEX

Explanations

numerical data and metrics related to fitness and exercise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

æ¹¯

-0.15

saf

-0.14

 wast

-0.14

 Ð´Ð¾Ñģ

-0.14

iliz

-0.14

sembl

-0.13

odem

-0.13

 transl

-0.13

è´§

-0.13

POSITIVE LOGITS

 heart

0.26

 workouts

0.24

 Trainer

0.23

HR

0.23

 workout

0.21

heart

0.21

 Heart

0.21

/activity

0.21

cad

0.20

 trainer

0.20

Activations Density 0.088%

numerical data and metrics related to fitness and exercise

No Comments

No Known Activations