INDEX

Explanations

technical language related to permissions and capabilities in programming or system access

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

agar

-0.17

emu

-0.16

æĮ

-0.15

-0.14

 Bauer

-0.14

rava

-0.14

esson

-0.14

lant

-0.14

ãĤ¦ãĤ©

-0.13

Ã¨

-0.13

POSITIVE LOGITS

 authority

0.18

authority

0.17

gio

0.17

Authority

0.16

 unlimited

0.16

Ded

0.15

ÄĽn

0.15

æĿĥ

0.14

 alone

0.14

Ã½n

0.14

Activations Density 0.187%

technical language related to permissions and capabilities in programming or system access

No Comments

No Known Activations