INDEX

Explanations

numerical data related to performance or metrics in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

urma

-0.18

abcdefghijklmnop

-0.17

äºĮåįģ

-0.16

chema

-0.16

ÅĻÃŃd

-0.15

akat

-0.15

åįģåħ«

-0.15

dden

-0.15

elijk

-0.14

oÄį

-0.14

POSITIVE LOGITS

0.39

0.32

0.31

 three

0.25

0.24

0.23

 third

0.21

three

0.19

ï¼ĵ

0.19

Activations Density 0.396%

numerical data related to performance or metrics in various contexts

No Comments

No Known Activations