INDEX

Explanations

quotations and punctuation marks indicating speech or dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

flate

-0.17

erken

-0.15

alsex

-0.14

 îł

-0.14

GENCY

-0.14

artial

-0.14

 Seymour

-0.14

createTime

-0.13

ÃŃsto

-0.13

OnError

-0.13

POSITIVE LOGITS

ubber

0.15

 Formal

0.14

omes

0.14

recht

0.13

 Homes

0.13

ãĥ³ãĥĨãĤ£

0.13

 Leadership

0.13

ORE

0.13

 polish

0.13

/sn

0.13

Activations Density 0.087%

quotations and punctuation marks indicating speech or dialogue

No Comments

No Known Activations