INDEX

Explanations

instances of actions or events related to timelines and planning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 recently

-0.19

recent

-0.17

 lately

-0.16

ÄĽst

-0.16

łģ

-0.15

Recent

-0.15

 Recently

-0.15

 recent

-0.15

 Recent

-0.15

endant

-0.15

POSITIVE LOGITS

 tomorrow

1.27

 Tomorrow

1.09

Tomorrow

1.03

 Ð·Ð°Ð²ÑĤÑĢÐ°

0.77

Âłtom

0.75

tom

0.71

 maÃ±ana

0.67

tom

0.60

TOM

0.60

 next

0.57

Activations Density 0.368%

instances of actions or events related to timelines and planning

No Comments

No Known Activations