INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ouble

-0.15

ServletContext

-0.15

ennes

-0.14

del

-0.14

-0.13

ch

-0.13

 capacity

-0.13

 goodbye

-0.13

avig

-0.13

POSITIVE LOGITS

abay

0.17

aoke

0.14

Ã´i

0.14

gren

0.14

bower

0.14

 Burnett

0.14

Coder

0.14

venue

0.14

.timedelta

0.13

iag

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.