INDEX

Explanations

punctuation marks, particularly commas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 Charg

-0.16

,{"

-0.16

 Leban

-0.16

é«

-0.15

 KeyCode

-0.15

ypad

-0.15

togroup

-0.15

 serialVersionUID

-0.14

croft

-0.14

oq

-0.14

POSITIVE LOGITS

ahn

0.15

aining

0.15

 tear

0.15

/or

0.15

entina

0.14

Ã¯

0.14

or

0.14

ider

0.14

 Marino

0.14

 record

0.14

Activations Density 0.523%

punctuation marks, particularly commas

No Comments

No Known Activations