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

DMI

-0.16

éĢļ

-0.15

cdr

-0.14

ACHI

-0.14

antee

-0.13

_BO

-0.13

 Suns

-0.13

 volum

-0.13

tero

-0.13

BX

-0.13

POSITIVE LOGITS

ziej

0.18

indent

0.18

olley

0.17

enk

0.17

asse

0.16

DonaldTrump

0.16

ÙĨØ²

0.16

enames

0.15

[".

0.15

latent

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.