INDEX

Explanations

references to specific films or sequels

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

æĻ´

-0.18

agini

-0.16

oire

-0.16

enstein

-0.15

Coins

-0.15

åĥį

-0.15

 Coins

-0.14

 Vampire

-0.14

åĥ

-0.14

©

-0.14

POSITIVE LOGITS

 Cameron

0.30

 Avatar

0.29

 Pandora

0.28

Avatar

0.25

Na

0.24

 James

0.24

ameron

0.24

 avatar

0.22

 Pand

0.22

James

0.22

Activations Density 0.003%

references to specific films or sequels

No Comments

No Known Activations