INDEX

Explanations

relationships and interactions among people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ilip

-0.16

 åį

-0.15

avier

-0.14

 straw

-0.14

ocard

-0.14

cen

-0.14

egen

-0.14

yen

-0.13

illard

-0.13

¬¸

-0.13

POSITIVE LOGITS

 behind

0.94

 Behind

0.79

Behind

0.70

beh

0.62

 achter

0.52

 rear

0.46

 trailing

0.43

 hinter

0.40

_beh

0.37

 posterior

0.36

Activations Density 0.150%

relationships and interactions among people

No Comments

No Known Activations

relationships and interactions among people

No Comments

No Known Activations