INDEX

Explanations

references to authors and co-authorship in academic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ationale

-0.15

arest

-0.15

keleton

-0.14

 massaggi

-0.14

optgroup

-0.13

suite

-0.13

aceous

-0.13

.bunifuFlatButton

-0.13

ugin

-0.13

alin

-0.13

POSITIVE LOGITS

 author

1.17

 Author

0.99

author

0.98

 authors

0.96

Author

0.91

-author

0.85

.author

0.82

 AUTHOR

0.82

_author

0.81

ä½ľèĢħ

0.81

Activations Density 0.186%

references to authors and co-authorship in academic contexts

No Comments

No Known Activations