INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Contributor

-0.15

 Taste

-0.14

onia

-0.14

pering

-0.14

Fel

-0.14

.mount

-0.14

Rak

-0.14

elik

-0.14

 states

-0.14

edition

-0.14

POSITIVE LOGITS

ì£

0.16

nof

0.15

ãģ¤ãģĳ

0.14

 Trucks

0.14

hotmail

0.14

gn

0.14

arest

0.14

UnitTest

0.14

(disposing

0.14

ÈĻi

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.