INDEX

Explanations

terms related to health conditions and wellness factors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

elsing

-0.15

uhe

-0.15

izin

-0.14

omnia

-0.14

ahi

-0.14

pling

-0.13

orgh

-0.13

æŃ

-0.13

_ADC

-0.13

 mortality

-0.13

POSITIVE LOGITS

 exposure

0.29

 exposures

0.27

 trauma

0.27

Tra

0.25

 Exposure

0.23

 diet

0.23

tra

0.23

 stress

0.22

 stren

0.22

 certain

0.22

Activations Density 0.222%

terms related to health conditions and wellness factors

No Comments

No Known Activations