INDEX

Explanations

medical conditions and symptoms associated with health

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oker

-0.18

 itself

-0.18

.scalablytyped

-0.17

 KÃ¼r

-0.15

äºľ

-0.15

Uvs

-0.14

çļĦä¸Ģä¸ª

-0.14

iesta

-0.14

.crm

-0.14

à¤¯à¤°

-0.14

POSITIVE LOGITS

 respectively

0.56

 alike

0.42

 respective

0.39

åĪĨåĪ«

0.34

 ê°ģê°ģ

0.29

 ÑģÐ¾Ð¾ÑĤÐ²ÐµÑĤ

0.27

ãģĿãĤĮ

0.22

respect

0.22

 both

0.20

 ambos

0.19

Activations Density 0.634%

medical conditions and symptoms associated with health

No Comments

No Known Activations