INDEX

Explanations

structured data or coding elements related to requests and results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ocha

-0.17

pha

-0.15

å¦Ĥä¸ĭ

-0.14

AppName

-0.14

aurus

-0.13

,eg

-0.13

angler

-0.13

.Encoding

-0.13

ÑĤÐ°ÐºÐ¸

-0.13

POSITIVE LOGITS

 above

0.30

 Above

0.25

Above

0.23

above

0.22

 ABOVE

0.21

 vÃ½Å¡e

0.17

ä»¥ä¸Ĭ

0.17

 hereby

0.16

bove

0.16

 this

0.16

Activations Density 0.147%

structured data or coding elements related to requests and results

No Comments

No Known Activations