INDEX

Explanations

expressions of gratitude and appreciation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Ã»

-0.14

oler

-0.14

Ð¾ÑĢÐ¾Ð´

-0.13

æĹıèĩªæ²»

-0.13

umm

-0.12

ourage

-0.12

 toler

-0.12

toa

-0.12

 Ð¶Ðµ

-0.12

taj

-0.12

POSITIVE LOGITS

 thanks

0.77

 thank

0.77

 Thanks

0.71

 Thank

0.67

 THANK

0.67

thanks

0.66

Thanks

0.66

thank

0.62

Thank

0.61

 gracias

0.59

Activations Density 0.363%

expressions of gratitude and appreciation

No Comments

No Known Activations