INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

deaux

-0.15

uida

-0.14

 bindActionCreators

-0.14

oslav

-0.14

agine

-0.14

obo

-0.14

sta

-0.14

'gc

-0.14

ÅĤu

-0.14

 Saul

-0.13

POSITIVE LOGITS

 habit

0.18

 Mess

0.16

 Fowler

0.14

 Giov

0.13

isphere

0.13

éĮ

0.13

inden

0.13

aab

0.13

_UNS

0.13

 Morrison

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.