INDEX

Explanations

references to characters who experience personal growth or transformation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 Hayward

-0.17

partment

-0.15

ilm

-0.15

ê³¡

-0.14

 Glob

-0.14

 sing

-0.14

 ISSN

-0.14

bler

-0.13

mov

-0.13

legates

-0.13

POSITIVE LOGITS

 novel

0.33

 novels

0.29

 Novel

0.25

nov

0.22

 book

0.21

 author

0.21

 books

0.21

 audi

0.20

 fiction

0.19

 Author

0.19

Activations Density 0.477%

references to characters who experience personal growth or transformation

No Comments

No Known Activations