INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

Sag

-0.15

 itself

-0.15

indi

-0.14

osg

-0.14

ä»ĺãģĳ

-0.14

ADM

-0.14

otron

-0.14

 particul

-0.13

_ENCODING

-0.13

lod

-0.13

POSITIVE LOGITS

fsp

0.16

Neal

0.16

atum

0.15

THON

0.15

egin

0.14

asin

0.14

à¤¥

0.14

iser

0.14

annel

0.14

enable

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.