INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Fol

-0.15

BX

-0.14

visor

-0.14

Bracket

-0.14

ungan

-0.13

æĸĻçĲĨ

-0.13

fol

-0.13

iyon

-0.13

ivet

-0.13

anzi

-0.13

POSITIVE LOGITS

arel

0.16

azor

0.15

Ø´Ø©

0.14

 ì¶ľìŀ¥

0.14

ÙĩØ¯

0.14

èĸ

0.14

á»Ł

0.14

anela

0.14

 Hudson

0.13

chai

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.