INDEX

Explanations

phrases and terms related to drawing attention and engagement

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

-0.15

orman

-0.14

hist

-0.14

ÐµÑī

-0.14

æ¨

-0.13

ÐµÐ»Ð°

-0.13

avicon

-0.13

æĬ±

-0.13

venir

-0.13

apo

-0.13

POSITIVE LOGITS

 attention

0.97

attention

0.81

 Attention

0.78

Attention

0.70

 attent

0.60

 atenciÃ³n

0.59

_attention

0.59

 Ð²Ð½Ð¸Ð¼Ð°Ð½Ð¸Ðµ

0.59

æ³¨æĦı

0.54

 attn

0.50

Activations Density 0.133%

phrases and terms related to drawing attention and engagement

No Comments

No Known Activations