INDEX

Explanations

mentions of cancer and related medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

.deb

-0.16

 Holmes

-0.14

odyn

-0.14

Å¡en

-0.14

onaut

-0.13

 thÃ´i

-0.13

 bern

-0.13

 escorte

-0.13

 Redistribution

-0.13

POSITIVE LOGITS

 cancer

0.26

 cancers

0.25

 tumors

0.24

 carcinoma

0.22

 Cancer

0.22

sar

0.21

squ

0.20

 malignant

0.20

coma

0.19

 malign

0.19

Activations Density 0.059%

mentions of cancer and related medical conditions

No Comments

No Known Activations