INDEX

Explanations

references to possession and relationships in familial or parental contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 sisters

-0.26

 siblings

-0.23

 grandfather

-0.21

 cousins

-0.21

 granddaughter

-0.21

 Cousins

-0.20

 Sisters

-0.20

 brothers

-0.19

 sister

-0.19

 Brothers

-0.19

POSITIVE LOGITS

 child

0.17

 beloved

0.16

 athlete

0.15

child

0.15

Child

0.15

 Child

0.15

æķı

0.14

ÎŃÏģ

0.14

 darling

0.14

kid

0.14

Activations Density 0.075%

references to possession and relationships in familial or parental contexts

No Comments

No Known Activations