INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Äĩi

-0.16

ãģĵ

-0.14

nameof

-0.14

 Sist

-0.14

Äĩ

-0.14

 Caldwell

-0.13

 neph

-0.13

quot

-0.13

inan

-0.13

 Anadolu

-0.13

POSITIVE LOGITS

itten

0.18

our

0.16

 noss

0.15

åł´

0.14

è¦ª

0.14

 nossa

0.14

formats

0.14

 Sung

0.13

 vÃ¥r

0.13

Ð´ÐµÑĢ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.