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

iasm

-0.16

oyer

-0.15

Carrier

-0.15

abus

-0.15

 Reform

-0.14

WARDED

-0.14

eto

-0.14

Urb

-0.14

COORD

-0.14

ì¹¨

-0.14

POSITIVE LOGITS

regor

0.15

 è£

0.14

utter

0.13

anela

0.13

 BirliÄŁi

0.13

 marque

0.13

Helmet

0.13

 dimin

0.13

okie

0.13

 Seek

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.