INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

lashes

-0.15

itably

-0.15

ERO

-0.14

 pornstar

-0.14

%(

-0.14

 vitam

-0.14

\grid

-0.14

ystore

-0.14

kop

-0.13

vÅ¯

-0.13

POSITIVE LOGITS

 overall

0.16

jian

0.16

overall

0.15

arga

0.15

æĻ¨

0.15

 specifics

0.14

(Editor

0.14

ontology

0.14

ago

0.14

 mainly

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.