INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

co

-0.16

 Mess

-0.15

åĴ

-0.14

OF

-0.14

 quá»¹

-0.14

iÄį

-0.13

abs

-0.13

ä»ĭ

-0.13

itch

-0.13

cent

-0.13

POSITIVE LOGITS

.xz

0.16

uvo

0.16

ucas

0.15

 Likely

0.14

gio

0.14

buc

0.14

Ð»Ð°Ñĩ

0.14

.Ordinal

0.14

Ð¶ÐµÐ½ÑĮ

0.13

ãģĦãģ¦

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.