INDEX

Explanations

file formats and figures in a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

jang

-0.18

 lateral

-0.15

visor

-0.14

trial

-0.14

ropol

-0.14

innie

-0.14

uess

-0.14

afe

-0.14

 trial

-0.13

sted

-0.13

POSITIVE LOGITS

annotate

0.15

RuntimeObject

0.15

ãĥ¼ãĥĨãĤ£

0.14

ernote

0.14

GuidId

0.14

iles

0.14

\OptionsResolver

0.14

ILES

0.14

 XmlNode

0.13

:CGRect

0.13

Activations Density 0.010%

file formats and figures in a document

No Comments

No Known Activations