INDEX

Explanations

concepts related to independence and separation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ousel

-0.13

oga

-0.13

Ãło

-0.12

okrat

-0.12

otic

-0.12

Zus

-0.12

amaz

-0.12

oram

-0.12

ÑģÑĤÑİ

-0.12

å¯¸

-0.12

POSITIVE LOGITS

 separate

1.19

 Separate

1.03

 seperate

1.00

 separately

0.91

 separ

0.85

Separ

0.83

 separated

0.82

 Separ

0.77

 independent

0.73

 separates

0.73

Activations Density 0.730%

concepts related to independence and separation

No Comments

No Known Activations