INDEX

Explanations

calls to action and engagement prompts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

à¸ĵ

-0.16

 Rencontres

-0.16

ikat

-0.15

venes

-0.15

linger

-0.14

kÃ¡nÃŃ

-0.14

nila

-0.14

erif

-0.14

/Gate

-0.14

reso

-0.14

POSITIVE LOGITS

pan

0.17

chester

0.15

 Masc

0.15

quer

0.14

pan

0.14

oretical

0.14

 weld

0.14

å®Įæķ´

0.14

unf

0.14

 reload

0.14

Activations Density 0.391%

calls to action and engagement prompts

No Comments

No Known Activations