INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 sÄĥ

-0.15

Ä±rak

-0.14

okrat

-0.13

Æ°ng

-0.13

SEA

-0.13

 templ

-0.13

Sta

-0.13

 tenant

-0.13

eker

-0.12

 PartialView

-0.12

POSITIVE LOGITS

TO

0.84

TO

0.84

-To

0.83

-to

0.79

To

0.74

_To

0.69

To

0.69

.to

0.68

_TO

0.68

_to

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.