INDEX

Explanations

phrases indicating personal states 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 @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 activeClassName

-0.15

ÑĢÐ°ÑĤ

-0.15

riend

-0.14

Repeated

-0.14

IGHL

-0.14

engo

-0.14

ÏģÏİÎ½

-0.13

VERBOSE

-0.13

ottage

-0.13

foy

-0.13

POSITIVE LOGITS

 done

0.32

 back

0.28

 DONE

0.27

 past

0.26

 through

0.26

 finished

0.24

 settled

0.23

 halfway

0.23

 onto

0.23

 ready

0.23

Activations Density 0.178%

phrases indicating personal states or experiences

No Comments

No Known Activations