INDEX

Explanations

references to family and kinship

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ãĤµãĥ¼

-0.15

/cop

-0.14

ãĤ¿ãĥ¼

-0.14

 Seit

-0.13

 Blessed

-0.13

reuse

-0.13

 Blitz

-0.13

//~

-0.13

imas

-0.13

anny

-0.13

POSITIVE LOGITS

 famil

0.24

 famille

0.18

 family

0.18

amilia

0.18

odesk

0.16

family

0.16

 families

0.16

alic

0.15

 familia

0.15

 Famil

0.15

Activations Density 0.004%

references to family and kinship

No Comments

No Known Activations