INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ÑĪÐ¾Ð²

-0.15

letics

-0.14

AGO

-0.13

.Expr

-0.13

senal

-0.13

Ã´m

-0.13

_GU

-0.13

venir

-0.13

vere

-0.13

vars

-0.13

POSITIVE LOGITS

 Plus

0.29

 indeed

0.29

And

0.29

 Indeed

0.28

Furthermore

0.27

Moreover

0.27

 Sure

0.26

 moreover

0.26

 Moreover

0.25

 furthermore

0.25

Activations Density 0.759%

No Comments

No Known Activations