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

ulaire

-0.15

antan

-0.15

idden

-0.15

ëŁ´

-0.15

ãĥ¬ãĥ¼

-0.14

ksi

-0.14

aggi

-0.14

 Counter

-0.14

kla

-0.13

ÙģÙĨ

-0.13

POSITIVE LOGITS

 Oscars

0.14

etty

0.14

ernel

0.14

ody

0.14

egie

0.13

/operators

0.13

 Dann

0.13

æ·

0.13

erosis

0.13

china

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.