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

als

-0.19

ffe

-0.18

ument

-0.17

vale

-0.16

uring

-0.15

pal

-0.15

sap

-0.15

-0.14

lando

-0.14

'&#

-0.14

POSITIVE LOGITS

lico

0.22

izabeth

0.16

ucid

0.15

æĮĻ

0.15

ãĥ³ãĤ¯

0.15

enu

0.15

iot

0.15

ldr

0.15

Ã©fono

0.14

Activations Density 0.052%

No Comments

No Known Activations