INDEX

Explanations

technical terms and concepts related to quantum mechanics and measurement theory

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

wan

-0.17

uan

-0.15

fld

-0.15

ivor

-0.15

é¡

-0.15

prox

-0.14

APA

-0.14

olia

-0.14

viso

-0.14

ZA

-0.14

POSITIVE LOGITS

 Walls

0.16

åĭĴ

0.15

izedName

0.15

pon

0.15

aleigh

0.14

ethe

0.14

 Squad

0.14

ques

0.14

ooter

0.13

altar

0.13

Activations Density 0.004%

technical terms and concepts related to quantum mechanics and measurement theory

No Comments

No Known Activations