INDEX

Explanations

instances of significant nouns and phrases that denote impact or importance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 opportunity

-0.19

 entire

-0.17

 likes

-0.17

 stuff

-0.17

 avenue

-0.16

 idea

-0.15

stuff

-0.15

ä¸Ģæ¬¡

-0.15

 approach

-0.14

 hint

-0.14

POSITIVE LOGITS

few

0.41

few

0.34

 many

0.32

Few

0.30

Few

0.29

many

0.29

åĩłä¸ª

0.25

 several

0.24

 ways

0.24

 MANY

0.24

Activations Density 0.181%

instances of significant nouns and phrases that denote impact or importance

No Comments

No Known Activations