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

à¸§à¸¥

-0.16

ppy

-0.15

ieu

-0.15

ube

-0.15

nds

-0.14

ulaire

-0.14

kul

-0.14

Å¡ku

-0.14

UGIN

-0.14

_DECL

-0.14

POSITIVE LOGITS

 Nach

0.15

 Petro

0.14

Fabric

0.14

Deferred

0.14

allax

0.14

uli

0.14

ãĤ·ãĤ¢

0.14

ev

0.13

 Pins

0.13

Wig

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.