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

 _______,

-0.20

.scalablytyped

-0.17

YPRE

-0.16

 litres

-0.16

istributed

-0.15

 metres

-0.14

 litre

-0.14

æľĭ

-0.14

isContained

-0.14

 Distributed

-0.14

POSITIVE LOGITS

ewe

0.18

 Nature

0.17

 Herr

0.17

 SYMBOL

0.15

VIA

0.15

Â»

0.15

Symbols

0.14

 symbolic

0.14

 symbol

0.14

pesan

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.