INDEX

Explanations

phrases indicating relationships and character development in narratives

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

 Rodney

-0.17

azen

-0.16

ãĤ«ãĥ¼ãĥī

-0.15

odont

-0.15

azon

-0.15

ponder

-0.15

Card

-0.15

oking

-0.14

.Card

-0.14

 Rena

-0.14

POSITIVE LOGITS

 Randall

0.29

 Pearson

0.28

Rand

0.24

 Toby

0.24

 Philadelphia

0.23

pear

0.23

Pear

0.22

 pear

0.22

 Pear

0.21

 Jack

0.21

Activations Density 0.004%

phrases indicating relationships and character development in narratives

No Comments

No Known Activations