INDEX

Explanations

references to specific individuals and their contributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

entiful

-0.16

McM

-0.16

 pioneered

-0.16

 CommonModule

-0.15

 experimented

-0.15

edata

-0.14

à¤°à¤¤

-0.14

 Yates

-0.13

notated

-0.13

 reporting

-0.13

POSITIVE LOGITS

 wanted

0.29

wanted

0.24

 hope

0.24

 originally

0.23

 hopes

0.20

 personally

0.19

 Wanted

0.18

 chose

0.18

 explains

0.18

hope

0.17

Activations Density 0.197%

references to specific individuals and their contributions

No Comments

No Known Activations