INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ertia

-0.18

keit

-0.17

oui

-0.16

ayne

-0.14

urname

-0.14

soever

-0.14

ayed

-0.14

-Isl

-0.14

-Muslim

-0.14

beit

-0.14

POSITIVE LOGITS

Rim

0.15

exter

0.14

 whenever

0.14

angu

0.13

ëĦ·

0.13

pest

0.13

rozen

0.13

 Nicol

0.13

LEM

0.13

ume

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.