INDEX

Explanations

interactions and relationships between people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

éĽĨä¸Ń

-0.16

ozilla

-0.15

inton

-0.14

assi

-0.14

arnation

-0.14

 Relationships

-0.14

borg

-0.14

 relationships

-0.14

IFI

-0.14

relude

-0.14

POSITIVE LOGITS

 exchange

0.30

 agree

0.26

exchange

0.26

 alike

0.26

 both

0.25

 BOTH

0.25

 share

0.25

 exchanged

0.25

 agreed

0.24

 Exchange

0.24

Activations Density 0.332%

interactions and relationships between people

No Comments

No Known Activations