INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

.Apis

-0.16

/tcp

-0.15

olist

-0.15

ikk

-0.14

wel

-0.14

Ð¾Ð»Ð¶

-0.14

eling

-0.14

á¿ĸ

-0.14

elas

-0.14

igo

-0.14

POSITIVE LOGITS

áº¥n

0.15

eca

0.15

äºľ

0.14

irim

0.14

LÄ°

0.14

erable

0.14

esz

0.14

 fluid

0.14

,std

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.