INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

acam

-0.15

 sucking

-0.15

dp

-0.14

Destructor

-0.14

 POSSIBILITY

-0.14

xo

-0.14

Poss

-0.14

RETURN

-0.14

Vu

-0.13

æ³£

-0.13

POSITIVE LOGITS

ots

0.17

elyn

0.15

Î¼Î¯

0.15

avenport

0.15

 GOODMAN

0.14

given

0.14

 dresser

0.14

jee

0.14

kot

0.14

 MetroFramework

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.