INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ĽĦ

-0.16

-0.14

oly

-0.14

ãĢİ

-0.14

erea

-0.13

 readers

-0.13

AGED

-0.13

Î¼Î¿Î½

-0.13

 Knox

-0.13

insert

-0.13

POSITIVE LOGITS

 ÃĤu

0.18

idy

0.16

 Budd

0.15

 Prem

0.15

 Gaut

0.14

uh

0.14

Prem

0.14

ragment

0.14

Dah

0.14

createFrom

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.