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

AdapterFactory

-0.17

å¢ĥ

-0.16

rex

-0.15

 Ð»ÑĸÐº

-0.14

ToInt

-0.14

à¥ģà¤¹

-0.14

_FP

-0.13

ç¼

-0.13

emonic

-0.13

łĢ

-0.13

POSITIVE LOGITS

olle

0.17

verse

0.15

pte

0.15

 computer

0.14

ieber

0.14

arness

0.14

oldem

0.14

axe

0.14

munition

0.14

fel

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.