INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

alls

-0.16

ayd

-0.15

pek

-0.15

ouser

-0.14

vier

-0.14

achel

-0.14

åĵ

-0.14

pek

-0.14

jom

-0.13

adas

-0.13

POSITIVE LOGITS

yor

0.14

 fucks

0.14

 escorte

0.13

ÂĽ

0.13

 cazzo

0.13

ãĥ¼ãĥ©

0.13

UIL

0.13

haf

0.12

-pill

0.12

boru

0.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.