INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

enor

-0.15

gon

-0.15

ipelines

-0.15

abay

-0.14

arend

-0.14

imits

-0.14

elon

-0.14

romium

-0.14

éĻ°

-0.14

abel

-0.13

POSITIVE LOGITS

tm

0.14

 Barry

0.14

 Dion

0.14

argout

0.13

argin

0.13

XCT

0.13

ieri

0.13

anela

0.13

PCP

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.