INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 expected

-0.15

GINE

-0.15

indo

-0.15

alue

-0.14

éĢł

-0.14

 Overnight

-0.13

 tart

-0.13

 among

-0.13

otas

-0.13

 tunes

-0.13

POSITIVE LOGITS

 Desire

0.26

 desire

0.26

 expenditure

0.25

 desires

0.23

 Couple

0.19

 expenditures

0.19

 Consumption

0.19

 Desired

0.18

 couples

0.17

 coupling

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.