INDEX

Explanations

terms associated with family dynamics and relationships

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

NECT

-0.15

IOC

-0.14

ITS

-0.14

åķĬåķĬ

-0.14

aeda

-0.13

ordon

-0.13

ote

-0.13

olec

-0.13

ITS

-0.13

outu

-0.13

POSITIVE LOGITS

0.45

 perhaps

0.41

 maybe

0.33

perhaps

0.32

 meth

0.31

 Perhaps

0.28

 really

0.28

maybe

0.26

Perhaps

0.26

 apparently

0.25

Activations Density 0.538%

terms associated with family dynamics and relationships

No Comments

No Known Activations