INDEX

Explanations

indicators of digital content availability and user engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

pto

-0.18

AIT

-0.17

uda

-0.15

OCUS

-0.15

hi

-0.15

udas

-0.14

yro

-0.14

imal

-0.14

aped

-0.14

ÏģÎº

-0.14

POSITIVE LOGITS

 atleast

0.81

èĩ³å°ĳ

0.67

 least

0.63

 alespoÅĪ

0.62

 Least

0.51

least

0.51

 ÑħÐ¾ÑĤÑı

0.46

Least

0.43

 ØŃØ¯Ø§ÙĤÙĦ

0.39

_least

0.38

Activations Density 0.340%

indicators of digital content availability and user engagement

No Comments

No Known Activations