INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

atatype

-0.15

DEX

-0.15

aler

-0.15

ooter

-0.15

 acos

-0.15

stm

-0.15

rex

-0.15

iko

-0.14

globals

-0.14

hari

-0.14

POSITIVE LOGITS

elve

0.18

uth

0.16

èĦ±

0.15

addle

0.15

 ApplicationDbContext

0.14

Jas

0.14

 Colbert

0.13

.ta

0.13

 Hover

0.13

åĨ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.