INDEX

Explanations

dates and times related to events or activities

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

jan

-0.32

-Jan

-0.26

JAN

-0.26

jan

-0.25

Jan

-0.25

Jan

-0.25

 Janet

-0.21

-Dec

-0.21

-Feb

-0.21

-Nov

-0.20

POSITIVE LOGITS

Jul

0.47

 July

0.46

Jul

0.43

JUL

0.43

July

0.42

 August

0.39

Aug

0.39

 augmentation

0.38

 augmented

0.37

aug

0.36

Activations Density 0.090%

dates and times related to events or activities

No Comments

No Known Activations