INDEX

Explanations

affirmations and expressions of personal opinion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Sail

-0.17

estre

-0.16

ullo

-0.16

ÑĴ

-0.15

]={↵

-0.15

´Ŀ

-0.14

ä¸įå¾Ĺ

-0.14

à¸£à¸²à¸¢

-0.14

æĺŃ

-0.14

 whereas

-0.14

POSITIVE LOGITS

yes

0.33

yes

0.32

Yes

0.27

Yes

0.27

YES

0.26

 indeed

0.26

YES

0.23

=yes

0.21

Yep

0.19

.Yes

0.19

Activations Density 0.100%

affirmations and expressions of personal opinion

No Comments

No Known Activations