INDEX

Explanations

references to health-related topics, particularly those associated with ailments and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

oka

-0.14

dash

-0.14

nÃ©

-0.13

 bordel

-0.13

MENTS

-0.13

ÄĽle

-0.13

 transformative

-0.12

Pom

-0.12

DMI

-0.12

iment

-0.12

POSITIVE LOGITS

assin

0.18

adol

0.15

gili

0.14

linkplain

0.14

aph

0.13

ovich

0.13

 withheld

0.13

ansas

0.13

ews

0.13

avra

0.13

Activations Density 1.663%

references to health-related topics, particularly those associated with ailments and treatments

No Comments

No Known Activations