INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

odash

-0.17

 Whatsapp

-0.15

 Hier

-0.15

á»ĩ

-0.14

vara

-0.14

 [âĢ¦

-0.13

ibaba

-0.13

ÐºÐ¾ÑĤ

-0.13

 (Â«

-0.13

 “[

-0.13

POSITIVE LOGITS

 Brian

0.25

Brian

0.20

(ph

0.17

----↵

0.17

--↵

0.16

-----↵

0.16

 parole

0.16

 false

0.16

0.15

 society

0.15

Activations Density 0.000%

No Known Activations

This feature has no known activations.