INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 fontStyle

-0.15

nt

-0.14

adiens

-0.13

enta

-0.13

acters

-0.13

ATALOG

-0.13

aign

-0.13

Ø§Ø¯ÙĦ

-0.13

--

-0.13

ofire

-0.13

POSITIVE LOGITS

à¥įà¤®à¤ķ

0.15

 GÃ¼r

0.15

.setViewport

0.14

ÑĢÑĥÑĩ

0.13

Ø¹

0.13

_MAXIMUM

0.13

UZ

0.13

onis

0.13

/terms

0.13

 misconduct

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.