INDEX

Explanations

punctuation marks and sentence structure indicators within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

istrovstvÃŃ

-0.17

ces

-0.16

 Hats

-0.15

 twig

-0.14

orpion

-0.14

ÎºÎ·

-0.14

zew

-0.14

bish

-0.14

hra

-0.14

unts

-0.14

POSITIVE LOGITS

zym

0.17

idor

0.17

uber

0.16

ARS

0.15

iller

0.15

ÑīÐ¸Ðº

0.15

¬Ĥ

0.14

agini

0.14

ajaran

0.14

Activations Density 0.017%

punctuation marks and sentence structure indicators within the text

No Comments

No Known Activations