INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

abh

-0.15

utan

-0.15

FTA

-0.15

yny

-0.15

ħĮ

-0.14

indre

-0.14

yster

-0.14

opes

-0.14

zano

-0.14

ÑģÐºÐ»Ð°Ð´

-0.13

POSITIVE LOGITS

 Haus

0.17

vice

0.14

edList

0.14

ÙĪÙģ

0.13

redo

0.13

hoe

0.13

hack

0.13

æĥĬ

0.13

 McMaster

0.13

(Sprite

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.