INDEX

Explanations

references to relationships and their complexities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 BOTH

-0.25

 both

-0.24

both

-0.24

 Both

-0.21

Both

-0.21

 beide

-0.16

_BOTH

-0.16

 ambos

-0.16

 bÃ¥de

-0.15

 ALWAYS

-0.14

POSITIVE LOGITS

 even

0.17

even

0.15

 thing

0.15

 something

0.15

 soon

0.14

 incluso

0.14

 sogar

0.14

ancel

0.14

something

0.14

Activations Density 0.078%

references to relationships and their complexities

No Comments

No Known Activations