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

Raw

-0.15

nn

-0.15

ilter

-0.14

dl

-0.14

.Raw

-0.14

ooled

-0.13

 Kits

-0.13

aldi

-0.13

emi

-0.13

POSITIVE LOGITS

zew

0.17

Ä±rak

0.15

isContained

0.15

Hed

0.15

 TimeInterval

0.14

anguard

0.14

(~(

0.14

InSeconds

0.14

Ãªs

0.14

 Ø§Ø«

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.