INDEX

Explanations

references to specific actors and their roles in films

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

 BCHP

-0.16

andle

-0.15

 Glasgow

-0.14

ãĥĮ

-0.14

çĨĬ

-0.14

ryb

-0.14

Nx

-0.14

achten

-0.13

CPS

-0.13

azzi

-0.13

POSITIVE LOGITS

 Iron

0.48

 Stark

0.45

 Tony

0.41

Iron

0.38

Tony

0.33

 iron

0.32

IRON

0.31

 Armor

0.30

 Pepper

0.29

 armour

0.29

Activations Density 0.013%

references to specific actors and their roles in films

No Comments

No Known Activations