INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.17

hak

-0.14

haven

-0.14

Ì§

-0.14

RELEASE

-0.14

ÑĢÑİ

-0.14

eson

-0.13

 realised

-0.13

reuse

-0.13

Ð²

-0.13

POSITIVE LOGITS

 Constitutional

0.16

ãģ¡ãĤĩ

0.15

 Natural

0.15

à¹ĩà¸Ķ

0.15

 America

0.14

 Catholic

0.14

ialias

0.14

 tedy

0.14

-Americ

0.14

/******************************************************************************/↵

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.