INDEX

Explanations

phrases indicating relationships and interactions between characters in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

.nc

-0.15

erÃ§

-0.15

ibri

-0.15

 Sequ

-0.15

aylor

-0.14

 Klopp

-0.14

ÐĺÐ¢

-0.14

andex

-0.14

mite

-0.14

cak

-0.14

POSITIVE LOGITS

Mad

0.31

 Sterling

0.27

 Madison

0.26

Mad

0.24

 agency

0.24

 firm

0.24

 agencies

0.22

Don

0.22

 Weiner

0.22

ad

0.21

Activations Density 0.002%

phrases indicating relationships and interactions between characters in a narrative

No Comments

No Known Activations