INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

zero

-0.16

Òĳ

-0.14

Äĥn

-0.14

 Worldwide

-0.14

::*

-0.13

 siendo

-0.13

zahl

-0.13

ausal

-0.13

 Intl

-0.13

Ø¬Ø§ÙĨ

-0.13

POSITIVE LOGITS

ionic

0.14

)prepare

0.14

↵

0.14

 wealthiest

0.14

ÑĸÐ´Ð¾Ð¼

0.14

 privile

0.14

teenth

0.14

 spatial

0.14

ped

0.13

 rhet

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.