INDEX

Explanations

references to quantitative changes or variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

à¸¢à¸¡

-0.16

obia

-0.15

uma

-0.14

å±¤

-0.14

unner

-0.14

andalone

-0.13

kees

-0.13

ipop

-0.13

 pronto

-0.13

intendo

-0.13

POSITIVE LOGITS

 slight

0.83

 slightly

0.76

 minor

0.57

 slightest

0.52

 mildly

0.50

 mild

0.50

 Minor

0.47

minor

0.45

Minor

0.44

 modest

0.43

Activations Density 0.327%

references to quantitative changes or variations

No Comments

No Known Activations