INDEX

Explanations

descriptions related to architectural features and structures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÑıÐ¶

-0.15

otto

-0.15

orks

-0.15

 Kendrick

-0.15

Ð»Ð°Ð²

-0.15

ÐµÑı

-0.14

ä»½

-0.14

 Fork

-0.14

adies

-0.14

oyer

-0.14

POSITIVE LOGITS

 surface

0.29

 surfaces

0.26

 Surface

0.24

surface

0.23

Surface

0.22

Exposed

0.19

urface

0.18

_surface

0.17

 face

0.17

 facing

0.17

Activations Density 0.176%

descriptions related to architectural features and structures

No Comments

No Known Activations