INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

á»ĳi

-0.15

 è±

-0.15

ToObject

-0.15

pell

-0.15

iska

-0.15

PEnd

-0.15

&action

-0.14

nelle

-0.14

/Foundation

-0.14

BS

-0.14

POSITIVE LOGITS

åį·

0.17

ntag

0.14

æĪ

0.14

OTE

0.14

Man

0.14

orris

0.14

.shtml

0.13

 Columbia

0.13

oux

0.13

à¸Ļà¸Ķ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.