INDEX

Explanations

phrases and concepts related to success and human relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

 Bang

-0.17

 Beng

-0.16

 though

-0.16

quine

-0.16

Bor

-0.15

 Birmingham

-0.15

ìŀĲ

-0.15

/tos

-0.14

 bais

-0.14

-Sah

-0.14

POSITIVE LOGITS

 butt

0.62

 Butt

0.54

But

0.53

 Butler

0.52

But

0.52

butt

0.51

 Butter

0.51

 butter

0.48

 butcher

0.40

 butto

0.39

Activations Density 0.112%

phrases and concepts related to success and human relationships

No Comments

No Known Activations