INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

/XML

-0.15

iod

-0.14

mekte

-0.14

ingle

-0.14

zig

-0.14

oppers

-0.13

enarios

-0.13

ì¹¨

-0.13

Ð¾Ð»Ñİ

-0.13

elm

-0.13

POSITIVE LOGITS

 Tanzania

0.16

 Kenya

0.16

-gnu

0.16

 Africa

0.15

Afr

0.15

 donor

0.14

 bond

0.14

frica

0.14

 African

0.14

 Ghana

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.