INDEX

Explanations

context related to genealogical or historical family data

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

Jeremy

-0.17

adoo

-0.16

aylight

-0.15

éĻ½

-0.15

andal

-0.15

iare

-0.15

echn

-0.15

 Jeremy

-0.15

 Marilyn

-0.15

riere

-0.14

POSITIVE LOGITS

 Carrie

0.23

 Frank

0.21

Eth

0.21

 Pearl

0.21

 Oscar

0.20

izzie

0.20

 Emma

0.20

 Kate

0.18

 Charlie

0.18

 Katie

0.17

Activations Density 0.170%

context related to genealogical or historical family data

No Comments

No Known Activations