INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Ð¾Ð±Ð¾

-0.15

à¸¥à¸°

-0.14

 ÎłÎ±Ïģ

-0.14

[string

-0.13

íĤ¹

-0.13

IMIZE

-0.13

elerin

-0.13

 Ð²Ð·Ð³Ð»ÑıÐ´

-0.13

imson

-0.13

 Mutable

-0.13

POSITIVE LOGITS

anto

0.17

uers

0.16

 your

0.15

istrovstvÃŃ

0.15

afil

0.15

é¼

0.15

amente

0.14

asel

0.14

weetalert

0.14

mac

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.