INDEX

Explanations

references to containers and their contents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

åĪĢ

-0.15

 knots

-0.15

uds

-0.14

/lic

-0.14

.Serial

-0.14

 curtains

-0.14

 Curtain

-0.14

izon

-0.14

.defaults

-0.13

achs

-0.13

POSITIVE LOGITS

 containers

0.42

 container

0.41

 cups

0.39

 vessels

0.35

 vessel

0.35

 Containers

0.35

 Container

0.35

 bowl

0.34

Containers

0.33

Container

0.33

Activations Density 0.185%

references to containers and their contents

No Comments

No Known Activations

references to containers and their contents

No Comments

No Known Activations