INDEX

Explanations

references to significant events or relationships in personal narratives

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

/Dk

-0.15

Â°}

-0.13

 baÅŁÄ±na

-0.13

ÑĢÐµÑī

-0.13

ouce

-0.13

eczy

-0.13

 artÄ±k

-0.13

arer

-0.13

 Annunci

-0.12

uo

-0.12

POSITIVE LOGITS

 during

1.30

during

1.13

 durante

1.07

 During

1.07

During

1.01

 bÄĽhem

0.74

 wÃ¤hrend

0.73

 tijd

0.69

 Ø®ÙĦØ§ÙĦ

0.58

 sÄ±rasÄ±nda

0.54

Activations Density 0.977%

references to significant events or relationships in personal narratives

No Comments

No Known Activations