INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

igli

-0.18

ÑıÑĩ

-0.16

tura

-0.15

antal

-0.15

ispens

-0.14

YST

-0.14

ellan

-0.14

adil

-0.14

igua

-0.14

POSITIVE LOGITS

>NN

0.20

 Drum

0.15

 Liquid

0.14

umpt

0.14

>manual

0.14

reb

0.14

BufferSize

0.14

Ĳ

0.13

arc

0.13

liquid

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.