INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ecast

-0.15

 addCriterion

-0.14

ãĥªãĥ¼ãĤº

-0.13

éĤ£ç§į

-0.13

MemoryWarning

-0.13

 scor

-0.13

 gentleman

-0.13

.bundle

-0.13

éĤ£äºĽ

-0.13

.LayoutStyle

-0.13

POSITIVE LOGITS

ot

0.21

Ray

0.20

 Otto

0.20

Ray

0.19

ray

0.19

Glo

0.19

 Raymond

0.18

ray

0.18

OT

0.18

rays

0.18

Activations Density 0.000%

No Known Activations

This feature has no known activations.