INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

icari

-0.15

rray

-0.14

__(

-0.14

 Benson

-0.14

}?

-0.14

}s

-0.14

antro

-0.14

qv

-0.13

æŁ

-0.13

olini

-0.13

POSITIVE LOGITS

)=

0.15

ValuePair

0.15

elman

0.15

éļľ

0.14

uced

0.14

ellan

0.14

ç¾½

0.14

_SY

0.13

angel

0.13

Activations Density 0.343%

No Comments

No Known Activations