INDEX

Explanations

specific names and titles related to people, particularly in academic and professional contexts

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

kah

-0.18

anske

-0.16

 Zucker

-0.15

rouw

-0.15

 Mehr

-0.15

 milfs

-0.15

irts

-0.15

à¸ķà¸²

-0.15

agne

-0.15

à¸ģà¸£à¸£à¸¡

-0.14

POSITIVE LOGITS

pill

0.28

 Pill

0.26

 Pitch

0.23

 Sound

0.23

Sel

0.22

Ven

0.22

iah

0.22

-pill

0.22

 Sund

0.22

Sub

0.21

Activations Density 0.332%

specific names and titles related to people, particularly in academic and professional contexts

No Comments

No Known Activations