INDEX

Explanations

terms related to health, wellness, and lifestyle factors that influence well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

izin

-0.15

ahi

-0.15

à¥įà¤¤à¤ķ

-0.14

å°Ĭ

-0.14

evenodd

-0.13

elsing

-0.13

_Osc

-0.13

uent

-0.13

ptrdiff

-0.13

apat

-0.13

POSITIVE LOGITS

 exposure

0.32

 trauma

0.28

 exposures

0.28

 Exposure

0.24

Tra

0.24

tra

0.23

 stren

0.23

 stress

0.23

 environmental

0.23

 diet

0.22

Activations Density 0.245%

terms related to health, wellness, and lifestyle factors that influence well-being

No Comments

No Known Activations