INDEX

Explanations

references to character development and narrative structure

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

 Elliott

-0.18

 Stanley

-0.16

WW

-0.15

 Elliot

-0.14

 Strawberry

-0.14

etroit

-0.14

 Hawkins

-0.14

Î³Î³

-0.14

 Elastic

-0.14

/fontawesome

-0.14

POSITIVE LOGITS

 Jedi

0.32

Pad

0.30

Pad

0.26

pad

0.26

 Republic

0.26

 Sith

0.25

 Mandal

0.24

-pad

0.23

 Master

0.22

 Darth

0.22

Activations Density 0.016%

references to character development and narrative structure

No Comments

No Known Activations