INDEX

Explanations

terminology related to quantum states and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

essel

-0.18

-0.15

osaic

-0.15

ldr

-0.14

mus

-0.14

unei

-0.14

ESSAGES

-0.14

esel

-0.14

ess

-0.14

ui

-0.14

POSITIVE LOGITS

Åº

0.17

ewidth

0.16

Ø§ÛĮØª

0.15

 canh

0.14

aware

0.14

LETE

0.14

ÎºÎ®

0.14

herits

0.13

 Humans

0.13

enthal

0.13

Activations Density 0.003%

terminology related to quantum states and measurements

No Comments

No Known Activations