INDEX

Explanations

prompts for reader engagement and contribution

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

gor

-0.15

ya

-0.15

 Gord

-0.15

éģĶ

-0.14

 htonl

-0.14

ymous

-0.14

 Attached

-0.14

adic

-0.14

deb

-0.14

lemen

-0.13

POSITIVE LOGITS

urer

0.16

à¹ģà¸ľ

0.15

ëĮĢë¡ľ

0.14

owi

0.14

olo

0.14

ÑģÑĤÐ¸

0.14

enville

0.14

Ã¹y

0.14

argout

0.14

ools

0.13

Activations Density 0.095%

prompts for reader engagement and contribution

No Comments

No Known Activations