INDEX

Explanations

phrases indicating searches for specific services or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ostringstream

-0.17

izr

-0.16

notated

-0.15

oho

-0.14

ropa

-0.14

 Ð´Ð¾Ð³

-0.14

/Peak

-0.14

åŁ

-0.14

.ManyToMany

-0.13

/shared

-0.13

POSITIVE LOGITS

 something

0.28

something

0.24

Something

0.24

 Something

0.23

 etwas

0.21

 challenge

0.21

 alternatives

0.20

omething

0.19

 iets

0.18

 slightly

0.18

Activations Density 0.133%

phrases indicating searches for specific services or experiences

No Comments

No Known Activations