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

 daily

-0.15

amd

-0.14

Ø§Ø±Ø¨

-0.14

 Others

-0.14

 âģ

-0.13

£½

-0.13

Î»ÎŃÎ¿Î½

-0.13

meli

-0.13

Ã

-0.13

ainless

-0.13

POSITIVE LOGITS

éº»

0.17

bolt

0.15

 underway

0.14

bol

0.14

geist

0.14

Æ°á»Ľ

0.13

 catalogs

0.13

èĮĤ

0.13

isy

0.13

 kinds

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.