INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Nar

-0.17

ovol

-0.15

 dane

-0.15

 purification

-0.14

ete

-0.14

ingu

-0.14

 pair

-0.14

asty

-0.14

 Saras

-0.14

ahn

-0.13

POSITIVE LOGITS

Ø¢Ùħ

0.16

ecies

0.16

agli

0.15

è±

0.15

ICODE

0.15

eyin

0.15

YLES

0.15

agal

0.15

NCY

0.14

KHR

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.