INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

elik

-0.15

 Wilkinson

-0.15

eer

-0.14

 grading

-0.14

ITO

-0.13

ayne

-0.13

pto

-0.13

epad

-0.13

bsp

-0.13

POSITIVE LOGITS

gang

0.17

uÄį

0.15

ture

0.14

acement

0.14

ersive

0.14

 Sommer

0.14

tour

0.14

olume

0.14

tiv

0.13

ersion

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.