INDEX

Explanations

specific terms and phrases related to abilities or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Sioux

-0.17

 Sikh

-0.14

cheng

-0.14

elters

-0.14

/kubernetes

-0.14

 Jong

-0.14

 Sniper

-0.14

jang

-0.14

eyh

-0.13

 Carson

-0.13

POSITIVE LOGITS

Sab

0.38

 Spell

0.32

Sab

0.32

 witches

0.30

 spell

0.30

 Salem

0.30

 witch

0.29

 spells

0.28

 magic

0.27

 SPELL

0.27

Activations Density 0.003%

specific terms and phrases related to abilities or actions

No Comments

No Known Activations