INDEX

Explanations

references to medical conditions, treatments, and patient-related outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

GRE

-0.17

upo

-0.16

 fate

-0.16

emics

-0.14

 epile

-0.14

.Enqueue

-0.14

ooth

-0.14

ortality

-0.13

FORE

-0.13

 victim

-0.13

POSITIVE LOGITS

 mild

0.23

 moderate

0.23

 Moderate

0.20

 advanced

0.19

 Mild

0.18

 uncomp

0.17

 refr

0.17

 grade

0.17

idi

0.16

Moder

0.16

Activations Density 0.110%

references to medical conditions, treatments, and patient-related outcomes

No Comments

No Known Activations