INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Sharper

-0.13

strap

-0.13

ngh

-0.12

BOT

-0.12

.middleware

-0.12

 ErrorResponse

-0.12

stab

-0.12

 Ð²Ð¸Ðº

-0.12

THB

-0.12

/******/

-0.12

POSITIVE LOGITS

azi

0.15

altung

0.15

USA

0.15

.opensource

0.15

geo

0.15

USA

0.15

raq

0.14

arsi

0.14

odzi

0.14

asury

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.