INDEX

Explanations

emotional engagement and personal experiences

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

anton

-0.19

idor

-0.14

itta

-0.14

ida

-0.14

DDS

-0.14

ĸ

-0.14

elib

-0.14

ackers

-0.14

inci

-0.13

ozor

-0.13

POSITIVE LOGITS

it

0.25

 thereof

0.23

å®ĥ

0.20

 ÙħÙĨÙĩ

0.18

 Ø¨Ø¯Ø§ÙĨ

0.18

 nÃ³

0.17

them

0.17

 davon

0.17

à¸±à¸ļà¸¡

0.17

 ÙĦÙĩØ§

0.16

Activations Density 0.427%

emotional engagement and personal experiences

No Comments

No Known Activations