INDEX

Explanations

occurrences of the articles "a" and "an"

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

rega

-0.18

oga

-0.15

inya

-0.15

cott

-0.15

Ã¤tz

-0.15

adius

-0.14

gow

-0.14

ëĨ

-0.14

andro

-0.13

Hus

-0.13

POSITIVE LOGITS

 Wilkinson

0.15

 given

0.15

ame

0.14

MMdd

0.14

 Stevenson

0.14

 particular

0.13

 Kunst

0.13

fon

0.13

 Yine

0.13

Activations Density 0.211%

occurrences of the articles "a" and "an"

No Comments

No Known Activations