INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

SessionFactory

-0.16

SystemService

-0.15

cete

-0.15

dge

-0.14

avery

-0.13

trak

-0.13

ovny

-0.13

letes

-0.13

paque

-0.13

å²

-0.13

POSITIVE LOGITS

arten

0.17

oor

0.17

art

0.16

UpInside

0.15

iez

0.15

FK

0.15

aight

0.15

har

0.14

iej

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.