INDEX

Explanations

interjections and markers of dialogue or transition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 æ±

-0.14

è§¦

-0.14

istro

-0.14

seau

-0.14

 Ø§ÙĦÙĪ

-0.14

resizing

-0.14

ians

-0.13

 halted

-0.13

itten

-0.13

alic

-0.13

POSITIVE LOGITS

 headed

0.28

 heading

0.27

 return

0.25

è¿ĶåĽŀ

0.24

 resume

0.23

 depart

0.23

adj

0.22

heading

0.22

 Heading

0.21

return

0.21

Activations Density 0.484%

interjections and markers of dialogue or transition

No Comments

No Known Activations