INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 breaker

-0.15

atorium

-0.14

Ú¯Ø§ÙĨ

-0.14

ardo

-0.14

udio

-0.14

 Snape

-0.13

lobal

-0.13

 Wand

-0.13

usa

-0.13

owler

-0.13

POSITIVE LOGITS

 means

0.24

 Means

0.24

means

0.21

Means

0.20

 sharp

0.17

iges

0.16

 Morm

0.16

Mean

0.15

_means

0.15

ONO

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.