INDEX

Explanations

relationships and familial connections

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

ovah

-0.16

µ

-0.15

 Grandma

-0.14

ETERS

-0.14

yon

-0.14

ÑĪÑĤ

-0.14

Mrs

-0.14

iske

-0.14

loit

-0.14

ymes

-0.14

POSITIVE LOGITS

 brother

1.05

 brothers

1.01

 sister

0.94

 sisters

0.93

 sibling

0.91

 siblings

0.91

 Brother

0.86

 Brothers

0.79

 Sister

0.73

 Sisters

0.68

Activations Density 0.428%

relationships and familial connections

No Comments

No Known Activations