INDEX

Explanations

phrases that indicate relationships and interactions between people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

undi

-0.18

Storyboard

-0.15

iras

-0.15

ammer

-0.15

irst

-0.15

versible

-0.14

STANCE

-0.14

ãĥ©ãĥĥãĤ¯

-0.14

 ç©

-0.14

tility

-0.14

POSITIVE LOGITS

 fellow

0.30

 others

0.22

 other

0.21

 peers

0.20

other

0.19

 Fellow

0.18

 Others

0.17

 Other

0.16

OTHER

0.16

 otros

0.16

Activations Density 0.221%

phrases that indicate relationships and interactions between people

No Comments

No Known Activations