INDEX

Explanations

structured data regarding competitions or achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 èı²

-0.17

arie

-0.16

VertexArray

-0.15

PerPixel

-0.14

urovision

-0.14

IFA

-0.14

icina

-0.14

æŁĵ

-0.14

á»Ŀi

-0.14

decorators

-0.13

POSITIVE LOGITS

0.16

ÑĤÑĢÐ¾

0.15

aks

0.14

arent

0.14

 responsible

0.14

inks

0.14

 æ£

0.14

Activations Density 0.259%

structured data regarding competitions or achievements

No Comments

No Known Activations