INDEX

Explanations

structured data elements related to authors and titles

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

>NN

-0.15

ntax

-0.15

pk

-0.14

Eis

-0.14

ces

-0.14

>equals

-0.14

Î³Îµ

-0.14

 ÄĮes

-0.14

pan

-0.14

oes

-0.14

POSITIVE LOGITS

ive

0.16

 bulls

0.16

icago

0.15

 Rochester

0.15

spawn

0.14

ullah

0.13

avicon

0.13

æĻĵ

0.13

.aspect

0.13

inal

0.13

Activations Density 0.026%

structured data elements related to authors and titles

No Comments

No Known Activations