INDEX

Explanations

phrases and concepts related to societal structures and complexities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

aml

-0.15

æĶ¾åľ¨

-0.15

ouble

-0.15

ulet

-0.14

 tucked

-0.14

 isolated

-0.14

 squeezed

-0.14

alled

-0.14

uler

-0.13

éº

-0.13

POSITIVE LOGITS

 filled

0.56

filled

0.43

Filled

0.39

 full

0.36

 llen

0.33

 fill

0.32

 litter

0.31

 pepper

0.31

 populated

0.29

_filled

0.28

Activations Density 0.310%

phrases and concepts related to societal structures and complexities

No Comments

No Known Activations