INDEX

Explanations

actions related to giving and receiving

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

 EITHER

-0.18

ãģ¾ãģļ

-0.16

id

-0.16

 GOODMAN

-0.14

zaj

-0.14

ERCHANT

-0.14

à®¿

-0.14

uspend

-0.13

ghan

-0.13

ppard

-0.13

POSITIVE LOGITS

 other

0.32

 others

0.24

åħ¶ä»ĸ

0.22

 another

0.22

other

0.21

 also

0.21

 accompanying

0.20

 similarly

0.20

 corresponding

0.20

'autres

0.19

Activations Density 0.756%

actions related to giving and receiving

No Comments

No Known Activations