INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

imon

-0.17

eyer

-0.15

perimental

-0.15

ÑĩÐ°Ð¹

-0.14

acky

-0.14

 Ø±Ø¬

-0.14

jÃŃ

-0.14

ANI

-0.14

aths

-0.14

olas

-0.14

POSITIVE LOGITS

lt

0.15

ghi

0.14

 cris

0.14

IVERS

0.14

 Premium

0.14

lord

0.13

GIT

0.13

Î¼Î¼Î±

0.13

èĤĮ

0.13

enha

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.