INDEX

Explanations

references to familial relationships and roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 granddaughter

-0.19

 niece

-0.18

 prelim

-0.15

æľĭåıĭ

-0.15

 grandson

-0.15

 relatives

-0.15

 Relatives

-0.15

plib

-0.15

ãĥ³ãĥģ

-0.14

 nephew

-0.14

POSITIVE LOGITS

 oldest

0.64

 older

0.55

 eldest

0.55

 youngest

0.54

 elder

0.47

 younger

0.46

older

0.44

 Older

0.44

 Ã¤l

0.39

 ÑģÑĤÐ°ÑĢ

0.33

Activations Density 0.163%

references to familial relationships and roles

No Comments

No Known Activations

references to familial relationships and roles

No Comments

No Known Activations