INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

itol

-0.17

oral

-0.16

amam

-0.15

 Seznam

-0.15

nano

-0.15

agli

-0.15

 Closure

-0.15

ocl

-0.15

 noqa

-0.14

arges

-0.14

POSITIVE LOGITS

yonel

0.15

ĺ

0.15

ecided

0.14

umph

0.14

uja

0.14

bite

0.14

gow

0.14

0.13

erce

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.