INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

-0.25

yk

-0.22

yi

-0.20

yb

-0.20

lein

-0.19

ÛĮ

-0.17

yre

-0.17

uario

-0.17

orum

-0.16

POSITIVE LOGITS

bing

0.31

ilitation

0.30

bed

0.24

ber

0.24

ulous

0.22

oard

0.21

upaten

0.21

riel

0.21

bling

0.21

STRACT

0.21

Activations Density 0.031%

No Comments

No Known Activations