INDEX

Explanations

references to past relationships and feelings associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

esture

-0.14

arken

-0.14

#End

-0.14

/includes

-0.14

BOR

-0.13

idos

-0.13

adoo

-0.13

å·

-0.13

er

-0.13

 demand

-0.13

POSITIVE LOGITS

amps

0.15

erald

0.15

lag

0.15

uner

0.15

 Posting

0.14

owan

0.14

rim

0.13

rieb

0.13

 Kris

0.13

Activations Density 0.026%

references to past relationships and feelings associated with them

No Comments

No Known Activations