INDEX

Explanations

phrases related to medical conditions and their implications

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

ilos

-0.15

 pÅĻitom

-0.14

cko

-0.13

indle

-0.13

 nackte

-0.13

antor

-0.12

 zatÃŃm

-0.12

antas

-0.12

otron

-0.12

enis

-0.12

POSITIVE LOGITS

 after

1.18

after

0.96

 AFTER

0.87

 dopo

0.81

 After

0.81

_after

0.81

 Ð¿Ð¾ÑģÐ»Ðµ

0.81

After

0.79

-after

0.75

 efter

0.75

Activations Density 1.898%

phrases related to medical conditions and their implications

No Comments

No Known Activations