INDEX

Explanations

expressions of personal experiences and reflections related to the writing process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

//{{

-0.14

Unmarshaller

-0.11

BackingField

-0.11

æ´¾

-0.11

ImageContext

-0.10

_simps

-0.10

<quote

-0.10

 rebuilt

-0.10

regunta

-0.10

LookAndFeel

-0.10

POSITIVE LOGITS

 writing

0.80

 write

0.74

-writing

0.66

 writes

0.65

 Writing

0.65

writing

0.64

write

0.64

 Write

0.64

åĨĻ

0.64

 wrote

0.63

Activations Density 0.684%

expressions of personal experiences and reflections related to the writing process

No Comments

No Known Activations