INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.14

æ³ģ

-0.14

nas

-0.14

_ABORT

-0.14

 liberty

-0.14

 eBook

-0.13

 Whilst

-0.13

RuntimeException

-0.13

ouples

-0.13

 eBooks

-0.13

POSITIVE LOGITS

Experiment

0.15

 Hamm

0.15

quet

0.15

çħ

0.14

 experiments

0.13

OK

0.13

Enlarge

0.13

 pÃŃs

0.13

 kinds

0.13

CREMENT

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.