INDEX

Explanations

terms related to data analysis and epidemiological studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 correl

-0.17

á»ĳi

-0.16

 inheritance

-0.14

GO

-0.14

 BAÅŀ

-0.14

 purs

-0.14

asad

-0.13

 measurable

-0.13

åĳ¼

-0.13

 emotional

-0.13

POSITIVE LOGITS

smooth

0.21

Smooth

0.21

sex

0.20

 Smooth

0.19

 smoothed

0.19

 Synthetic

0.18

 synthetic

0.18

-sex

0.17

 crude

0.17

age

0.17

Activations Density 0.010%

terms related to data analysis and epidemiological studies

No Comments

No Known Activations

terms related to data analysis and epidemiological studies

No Comments

No Known Activations