INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oola

-0.18

inki

-0.15

loser

-0.15

izr

-0.14

 Schultz

-0.14

 Hairst

-0.14

deniz

-0.14

Ð»Ð°ÑĢÐ°

-0.14

agr

-0.13

unities

-0.13

POSITIVE LOGITS

 Pill

0.20

isContained

0.17

 Forge

0.16

_flash

0.14

ellar

0.14

Å¾e

0.14

ikt

0.14

WO

0.13

enton

0.13

ogs

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.