INDEX

Explanations

names of individuals and their professional accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 pictures

-0.21

 pics

-0.20

 photos

-0.20

 screenshots

-0.19

 drawings

-0.17

pictures

-0.17

 photographs

-0.16

essim

-0.15

 misd

-0.15

Pictures

-0.15

POSITIVE LOGITS

 wedding

0.25

 Landscape

0.24

 Wedding

0.24

 Canon

0.23

 Fine

0.23

 shooting

0.22

 gear

0.22

 Portrait

0.22

 assignment

0.21

 workflow

0.21

Activations Density 0.084%

names of individuals and their professional accomplishments

No Comments

No Known Activations