INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

inho

-0.18

å¹¸

-0.16

ello

-0.14

ãģĴ

-0.14

otron

-0.14

ÑĸÐ¶

-0.14

agment

-0.13

...

-0.13

Ign

-0.13

rement

-0.13

POSITIVE LOGITS

 sÄ±

0.16

"description

0.16

NECT

0.16

alse

0.15

PTY

0.14

 Afterwards

0.14

*sp

0.14

atal

0.14

"title

0.14

ertime

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.