INDEX

Explanations

instances of the word "invited" and related contexts of invitations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

wards

-0.16

enas

-0.15

ownik

-0.15

ynchronously

-0.15

.BorderFactory

-0.14

isson

-0.14

infeld

-0.14

idor

-0.14

åĻ¨

-0.14

POSITIVE LOGITS

 onto

0.19

-only

0.18

 participation

0.18

preneur

0.17

onto

0.17

ç¢¼

0.16

TargetException

0.16

 into

0.16

 guests

0.16

into

0.16

Activations Density 0.024%

instances of the word "invited" and related contexts of invitations

No Comments

No Known Activations