INDEX

Explanations

words expressing possibilities or potential outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

odem

-0.15

uff

-0.14

icont

-0.14

ÑģÑĤÐ²

-0.14

ÄĽr

-0.14

ÙĪÙĨÙĬØ©

-0.13

/*č↵

-0.13

atron

-0.13

isoner

-0.13

asons

-0.13

POSITIVE LOGITS

 soon

0.30

soon

0.24

 Soon

0.22

 headed

0.18

Soon

0.18

 sá»Ľm

0.18

 possibly

0.18

 eventually

0.17

 upcoming

0.17

 finally

0.17

Activations Density 0.104%

words expressing possibilities or potential outcomes

No Comments

No Known Activations