INDEX

Explanations

important linking words and phrases that connect ideas and sections in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

illo

-0.16

Î³Ïĩ

-0.15

 merits

-0.15

Ãªnh

-0.15

hea

-0.14

ÙĤÙħ

-0.14

ÅĻÃŃ

-0.14

aginator

-0.14

ories

-0.14

åĳĬ

-0.13

POSITIVE LOGITS

ede

0.19

usz

0.15

Ãło

0.15

0.14

 distance

0.14

ylvania

0.14

ìļ´ëıĻ

0.14

ing

0.14

 Distance

0.14

 Ingen

0.14

Activations Density 0.013%

important linking words and phrases that connect ideas and sections in text

No Comments

No Known Activations