INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

linger

-0.16

enco

-0.15

zn

-0.15

oya

-0.14

éľ

-0.14

acin

-0.13

akk

-0.13

outu

-0.13

uchi

-0.13

ppl

-0.13

POSITIVE LOGITS

ped

0.26

Ped

0.21

Kes

0.20

VT

0.18

KE

0.18

 Veterans

0.18

Ped

0.17

PED

0.17

 tied

0.17

åľĪ

0.17

Activations Density 0.000%

No Known Activations

This feature has no known activations.