INDEX

Explanations

references to rules, conditions, or considerations related to decision-making and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Appropri

-0.15

azon

-0.15

uin

-0.15

atism

-0.14

dam

-0.14

 metaphor

-0.14

 appropriately

-0.14

 preserving

-0.14

elsif

-0.14

lush

-0.13

POSITIVE LOGITS

 further

0.24

 Further

0.21

Further

0.21

 weitere

0.17

moire

0.17

loat

0.15

 think

0.15

ople

0.15

 luck

0.15

åĩºãģĹ

0.15

Activations Density 0.019%

references to rules, conditions, or considerations related to decision-making and evaluations

No Comments

No Known Activations