INDEX

Explanations

references to mystery and detective literature

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

ivec

-0.15

æ²ĸ

-0.14

apsed

-0.14

 troub

-0.14

Î³Î¿Ïħ

-0.14

otron

-0.14

æľĭ

-0.14

 Mellon

-0.14

elig

-0.14

.Flag

-0.13

POSITIVE LOGITS

 Herc

0.40

 Christie

0.35

 Hastings

0.28

Ag

0.25

 Miss

0.22

 Orient

0.22

 Inspector

0.21

 Belgian

0.20

Miss

0.20

 Belg

0.20

Activations Density 0.002%

references to mystery and detective literature

No Comments

No Known Activations