INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

engo

-0.16

endor

-0.16

aurant

-0.16

tek

-0.15

lix

-0.15

iglia

-0.15

peria

-0.15

rex

-0.15

chner

-0.15

erial

-0.14

POSITIVE LOGITS

addtogroup

0.14

OT

0.14

 Bray

0.14

 Ð¿ÐµÑĢÐµÐ±

0.13

Sensitive

0.13

 apar

0.13

-equiv

0.13

å©Ĩ

0.13

alink

0.13

ÃŃrk

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.