INDEX

Explanations

phrases indicating preparation or readiness for a task

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

çµĲ

-0.17

nette

-0.15

utations

-0.13

cum

-0.13

cf

-0.13

ox

-0.13

iÃ³

-0.13

kup

-0.13

Kat

-0.13

acker

-0.13

POSITIVE LOGITS

 next

0.45

now

0.42

now

0.37

next

0.37

 ÑĤÐµÐ¿ÐµÑĢÑĮ

0.36

 Next

0.36

Now

0.36

Next

0.35

 NEXT

0.35

Now

0.33

Activations Density 0.208%

phrases indicating preparation or readiness for a task

No Comments

No Known Activations