INDEX

Explanations

references to certification and compliance standards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

åªĴ

-0.20

 nÄĥ

-0.16

otoxic

-0.15

undler

-0.14

fÃ¼

-0.14

ctic

-0.14

iola

-0.14

Argb

-0.14

meld

-0.13

WWW

-0.13

POSITIVE LOGITS

arov

0.14

kovÃ©

0.14

kker

0.14

rophy

0.14

 Slug

0.14

iliz

0.14

rine

0.14

ewing

0.14

riangle

0.14

iangle

0.13

Activations Density 0.010%

references to certification and compliance standards

No Comments

No Known Activations