INDEX

Explanations

references to structured data and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 defy

-0.18

ist

-0.17

uler

-0.16

Lal

-0.15

åĦ¿

-0.15

Â®

-0.14

á»£

-0.14

www

-0.14

ard

-0.14

ier

-0.14

POSITIVE LOGITS

LOCKS

0.16

elong

0.16

aina

0.15

.GroupLayout

0.15

anship

0.15

RITE

0.15

ÌĤ

0.14

 IonicModule

0.14

uncture

0.14

amework

0.14

Activations Density 0.058%

references to structured data and their interactions

No Comments

No Known Activations